We humans confabulate, too – not only AI

As a scientist you have to learn and accept that our perception of the world and of the rules governing it may reflect more of our genetically designed and socially acquired prejudices than reality. Scientist go through a long training to mistrust our prejudices. They instead try to understand reality on a deeper level of experimental tests combined with the building of theories and verifiable predictions. On this background I want to discuss a specific aspect in the presently heated debate about the alleged dangers of A(G)I. An aspect which I think is at least in parts misunderstood and not grasped at its full extend.

A typical argument in the discussion, which is used to underline a critical view on AI, is: “AI as e.g. in the form of GPT4 makes things up. Therefore, we cannot trust it and therefore it can be dangerous.” I do not disagree. But the direction of the critics misses one important point: Are we humans actually better?

I would clearly say: Not so much as we like to believe. We still have a big advantage in comparison with AI: As we are embedded into the physical world and interact with it we can make clever experiments to explore underlying patterns of cause and action – and thus go beyond the detection of correlations. We also can test our ideas in conversations with others and in confrontation with their experiences. Not only in science, but in daily social interaction. However, to assume that we humans do not confabulate is a big mistake. Actually, the fact that large language models (and other models of AI) often “hallucinate” makes them more similar to human beings than many of newspaper journalists are willing to discuss in their interviews with AI celebrities.

Illustration: “Hallucinations” of a convolutional network trained on number patterns when confronted with an image of roses

Experiments in neurosciences and psychology indicate that we human beings probably confabulate almost all the time. At least much more often than we think. Our brain re-constructs our perception of the world according to plausibility criteria trained end developed both during evolution of mankind and during our personal life. And the brain presents us manipulated stories to give us a coherent and seemingly consistent view upon our interactions with reality and the respective time-line added to our memories.

You do not believe in a confabulation of our brain? Well, I do not want to bore you with links to a whole bunch of respective literature published during the last 3 decades on this subject. Sometimes simple things make the basic argument clear. One of these examples is an image that got viral on social media some years ago. I stumbled across it yesterday when I read an interview of the Quanta Magazine with the neuroscientist Anil Seth about the “nature of consciousness”. And I had a funny evening afterward with my wife due to this picture. We had a completely different perception of it and its displayed colors.

The image is “The dress” of Cecilia Bleasdale. You find it in the named and very informative interview of the Quanta Magazine. You also find it on Wikipedia. I refrain from showing it, as there may be legal right issues. The image displays a skirt.

A lot of people see it as an almost white skirt with golden stripes. Others see it as a blue skirt with almost black stripes. Personally, I see it as a lighter, but clearly blue skirt with darker bronze/golden stripes. But more interesting: My wife and I totally disagreed.

We disagreed on the colors both yesterday night and this morning – under different light conditions and looking at the image on different computer screens. Today we also looked at hex codes of the colors: I had to admit that the red, green, blue mixture in total indicates much darker stripes than I perceive them. But still the dominant red/green combination gives a clear indication of something of a darker gold. The blue areas of the skirt are undisputed between me and my wife, although I seemingly perceive it in a lighter shading than my wife.

This is a simple example of how our brain obviously tells us our own individual stories about reality. There are many other and much more complex examples. One of the most disputed one is the question of whether we really control our intentional behavior and related decisions at a period around the decision making. A whole line of experiments indicates that our brain only confabulates afterward that we were in control. Our awareness of decisions made under certain circumstances appears to be established some hundred milliseconds after our brain actually triggered our actions. This does not exclude that we may have a chance of control on longer timescales and by (re-) training and changing our decision making processes. But on short timescales our brain decides and simply acts. And this is good so. Because it enables us to react fast in critical situations. A handball player or a sword fencer does not have much time to reflect his or her actions; sportsmen and sportswomen very often rely on trained automatisms.

What can we be sure about regarding our perceptions? Well, physical reality is something different than what we perceive via the reaction of our nerve system (including the brain) to interactions with objects around our bodies and resulting stimuli. Or brain constructs a coherent perception of reality with the help of all our senses. The resulting imagination helps us to survive in our surroundings by permanently extrapolating and predicting relatively stable conditions and evolution of other objects around us. But a large part of that perception is imagination and our brain’s story telling. As physics and neuroscience has shown: We often have a faulty imagination of reality. On a fundamental level, but often enough also on the level of judging visual or acoustic information. Its one of the reasons why criminal prosecutors must be careful with the statements of eye-witnesses.

Accepting this allows for a different perspective on our human way of thinking and perceiving: Its not really me who is thinking. IT, the brain – a neural network – is doing it. IT works and produces imaginations I can live with. And the “I” is an embedded entity of my imagination of reality. Note that I am not disputing a free will with this. This is yet another and more complex discussion.

Now let us apply this skeptical view on human perception onto today’s AI. GPT without doubt makes things up. It confabulates on the background of already biased information used during training. It is not yet able to check its statements via interactions with the physical world and experiments. But a combination of transformer technology, GAN-technology and Reinforcement Learning will create new and much more capable AI-systems soon. Already now interactions with simulated “worlds” are a major part of the ongoing research.

In such a context the confabulations of AI-systems make them more human than we may think and like. Let us face it: Confabulation is an expected side aspect on our path to future AGI-systems. It is not a failure. Confabulation is a feature we know very well from us human beings. And as with manipulative human beings we have to be very careful with whatever an AI produces as output. But fortunately enough AI-systems do not yet have an access to physical means to turn their confabulations into action.

This thought, in my opinion, should gain more weight in the discussion about the AI development to come. We should much more often ask ourselves whether we as human beings fulfill the criteria for a conscious intelligent system really so much better than these new kinds of information analyzing networks. I underline: I do not at all think that GPT is some self-conscious system. But the present progress is only a small step at an early stage of the development of capable AI. Upon this all leading experts agree. And we should be careful to give AI systems access to physical means and resources.

Not only do researchers see more and more emergent abilities of large language networks aside those capabilities the networks were trained for. But even some of the negative properties as confabulation indicate “human”-like sides of the networks. And there are overall similarities between humans and some types of AI networks regarding the basic learning of languages. See a respective link given below. These are signs of a development we all should not underestimate.

I recommend to read an interview with Geoffrey Hinton (the prize-winning father of back-propagation algorithms as the base of neural network optimization). He emphasizes the aspect of confabulation as something very noteworthy. Furthermore he claims that some capabilities of today’s AI networks already surpass those of human beings. One of these capabilities is obvious: During a relatively short training period much more raw knowledge than a human could process on a similar time scale gets integrated into the network’s optimization and calibration. Another point is the high flexibility of pre-trained models. In addition we have not yet heard about any experience with multiple GPT instances in a generative interaction and information exchange. But this is a likely direction of future experiments which may accelerate the development of something like an AGI. I give a link to an article of MIT Technology Review with Geoffrey Hinton below.

Links and articles

https://www.quantamagazine.org/ what-is-the-nature-of-consciousness-20230531/
https://slate.com/ technology/ 2017/04/ heres-why-people-saw-the-dress-differently.html
https://www.theguardian.com/ science/ head-quarters/ 2015/feb/27/ the-dress-blue-black-white-gold-vision-psychology-colour-constancy
https://www.technologyreview.com/ 2023/05/02/ 1072528/ geoffrey-hinton-google-why-scared-ai/
https://www.quantamagazine.org/ some-neural-networks-learn-language-like-humans-20230522/

 

Opensuse Leap 15.4 – Problems with Optimus and prime-select after updates of SW packages

Presently, I work a lot on an old laptop which has a so called Optimus combination of a dedicated Nvidia GPU and an Intel GPU coming with the main CPU-processor. “prime-select” is a tool which Opensuse includes with Leap 15.4 to provide an efficient way of controlling which GPU shall be used. As good as prime-select has worked for me on Leap 15.3 and also some time with Leap 15.4 recent updates of a variety of SW packages lead into trouble.

I had the Nvidia card active before the SW updates. After a cold restart of the system it did no longer start the SDDM display manager on the default systemd target. This happened even when the updates did not directly affect the kernel or the Nvidia kernel modules.

The problem always had to do with bbswitch turning off the Nvidia device when the system switched to the default graphical target. And with a turned off Nvidia graphics device the Nvidia drivers can not be loaded.

So some SW updates lead to a change of the configuration prime-select had set up before the updates. The stupid thing is that it is not quite so simple to get things back to work. To try to us “init 3” to go to a console interface on a non-graphical target and then use “prime-select nvidia” plus a subsequent “init 5” on the command line does not work. You do not change the wrong bbswitch actions that way. You can also turn bbswitch off by “tee /proc/acpi/bbswitch <<< OFF". And then load the Nvidia driver successfully. But trying to afterward switch to the standard graphical target invokes bbswitch again in the wrong way. It is a bit of a mess. The following steps seem to work to get back to normal operation again:

  • Step 1: Use “init 3” on a console terminal.
  • Step 2: Use the command “prime-select intel”.
  • Step 3: Restart your system. It should boot now into the graphical target based on the i915 intel GPU driver.
  • Step 4: Ignore any information from a prime-select icon. It shows you a plainly wrong info that you are using Nvidia.
  • Step 5: Log in as root on a root terminal window. Switch bbswitch off (e.g. by the command given above). Load the Nvidia module by “modprobe nvidia”. Check via lsmod that it is successfully loaded.
  • Step 6: Type in “prime-select nvidia”.
  • Step 7: Log out from your graphical interface.
  • Step 8: Check that SDDM or whatever display manager is started with bbswitch not shutting down the Nvidia card. Log inn with the Nvidia card active.
  • Step 9: Check that the Nvidia driver is still loaded on a root terminal window. Then issue “mkinitrd” and restart your Leap 15.4 system.

Afterward using the “prime-select intel” or “prime-select nvidia” commands at the command line of a root terminal window, a logout from the graphical desktop and a login again via the restarted graphical display manager switches correctly between the cards.

However, the prime-select applet gives you wrong information when the intel card is active. And it does not give you the chance to switch back to the Nvidia card again. Its stupid, but no major problem as long as the basic prime-select command does its job on the command line.

Hope this helps people having to work with Opensuse on an Optimus system.

 

Autoencoders and latent space fragmentation – X – a method to create suitable latent vectors for the generation of human face images

My present post series explores options to use a standard convolutional Autoencoder [AE] for the creation of images with human faces. The face generation should based on random input to the AE’s Decoder. On our quest for a suitable method we have meanwhile learned a lot about other aspects of Autoencoders, vector distributions in multi-dimensional latent spaces and generative methods for our special case:

  • Methods to create statistical latent vectors [z-vectors] as input for the AE’s Decoder must be chosen carefully. Among other things: It is difficult to create a bunch of random vectors which cover wider areas in the vastness of a multidimensional space. So the z-vector creation must be adjusted to specific requirements.
  • After having been trained with CelebA images a convolutional AE fills a limited and coherent region in the latent space with z-points for the training images. This latent space region appears to be critical for successful image creation: Statistically generated z-vectors should point to this region. The core of the z-point distribution gets filled relatively densely.
  • A convolutional AE maps human face images onto an approximate multivariate normal distribution. This gives the inner core of the z-point distribution the structure of a multidimensional ellipsoid. The projections of this ellipsoid onto 2-dimensional coordinate planes show characteristic nested elliptic contour lines.
  • As the main axes of these ellipses were inclined with different angle towards the axes of chosen coordinate planes we concluded that linear correlations mark average dependencies between the z-vector components. Limiting conditions imposed by these correlations must also be fulfilled by z-vectors used as the Decoder’s input.

See previous posts in this series for more details. In particular, the last 2 posts

Autoencoders and latent space fragmentation – IX – PCA transformation of the z-point distribution for CelebA

Autoencoders and latent space fragmentation – VIII – approximation of the latent vector distribution by a multivariate normal distribution and ellipses

have shown that the density distribution for the z-points really exhibits elliptic contour lines in the original coordinate system of the latent space and (!) in the target coordinate system of a PCA transformation.

In this post we use our gathered knowledge: I present a first simple method to generate z-vectors which point to the latent space region filled by z-points for CelebA images. These z-vectors will fulfill the general and limiting elliptic conditions for their components.

Decomposing the full problem of latent vector generation into a sequence of 2-dimensional problems

The nice thing about multivariate Gaussian distributions with linear correlations between the vector components is the following: We can reduce the problem of choosing proper component values to a series of 2-dimensional restrictions. Firstly we can use characteristic properties of the Gaussian distribution for each component. And secondly we can use confidence ellipses in 2-dimensional coordinate planes to restrict the component values to allowed intervals.

Ellipses are most easy to handle when their axes are aligned with the axes of the coordinate system in which we describe them. So, let us assume that we know an affine transformation T to a new coordinate system which also has orthogonal axes and supports the following special transformation properties for a multivariate normal density distribution:

  1. T maps nested elliptic contour lines of the multidimensional density distribution and in particular confidence ellipses for component pairs in the original coordinate system to nested elliptic contours and confidence ellipses in the new coordinate system.
  2. Taligns the centers of the transformed ellipses with the origin of the new coordinate system.
  3. T aligns the main axes of the mapped ellipses with the axes of the new coordinate system.
  4. T is reversible.

How could we then use the transformed data for vector-creation?

In the new coordinate system, a contour ellipse in a chosen coordinate plane for the axes-indices (i, j) may have main diameters of size

d1 = 2 * a    and    d2 = 2 * b.

We then can first select a random v_i value to fall into a range [-a * fact, a * fact].

fact * a    <    v_i    <    fact * a

With fact being a proper factor. This factor defines a confidence level in the new coordinate system. With the value of v_i fixed and b being the half-diameter in the orthogonal direction the correlation condition for the z-point distribution says that the v_j value must fall into an interval [-c, c] defined by:

-c    <    v_j    <    c,
with c = b * fact * sqrt(1 – x**2 / (fact * a)**2)

But within these limits we can again choose the v_j-value freely. Below I use a simple random-function for a constant probability density to pick a value.

However: It would not be enough to restrict the coordinates to the conditions of just one ellipse! The components of the created vectors must in parallel fulfill elliptic conditions for all of the possible pairs of vector-components. I.e. we may need to adapt the v_j values gained from the analysis of a fist 2D-ellipse to further conditions of other ellipses and component pairs. This can be achieved by an iteration. For z_dim = 256 this involves a total of 32640 checks and possible value-adaptions to each and all of the allowed value ranges.

In addition: The order by which the component-pairs and their conditions are investigated must be randomized to get real statistical vector distributions.

Eventually the resulting vector components must be re-transformed into the original coordinate system of the latent space.

The ellipse for the “core’s boundary” in the original coordinate system will be defined by the chosen confidence level of the ellipsoidal normal distribution. We saw already that a confidence level of σ = 2.0 defines the transition to outer regions of the z-point density distribution quite well.

This all sounds manageable by relative simple Python programs. But: Do we know a proper transformation T? Yes, we do: A PCA-transformation of the z-point density distribution has all the properties discussed above.

Using half maximum values after a PCA transformation of the z-point distribution

The last post proved that a PCA transformation maps ellipses onto ellipses for component pairs in the transformed PCA coordinate system. The advantage of the ellipses there is that their main axes are on average well aligned with the orthogonal PCA coordinate axes. Gaussians for the number density distribution per component are mapped to Gaussians for the new components in the transformed coordinate system. So, the basic idea for a proper z-vector generation is:

  1. Take the multivariate normal z-point distribution for the training images in the AE’s latent space.
  2. Apply a PCA analysis to diagonalize the correlation matrix and transform the z-vector components to the PCA coordinate system.
  3. Use the ellipses in coordinate planes of the PCA coordinate system to create random z-vector components fulfilling all required conditions there.
  4. Re-transform the resulting z-vector components into the original coordinate system of the latent space.

Point 3 in our method is covered by a numerical analysis of the Gaussians in the PCA-coordinate system. We determine the half-width numerically by analyzing the density distribution with the help of sampling intervals. This simple method has resolution limits related to the size of the sampling interval. This has consequences for PCA components with a small standard deviation. We saw already in the last posts that such distributions appear for higher PCA components at the lower end of the explained variance.

Does the suggested method work?

The convolutional AE we work with was defined in previous posts with 4 Conv2D layers in the Encoder and 4 Conv2DTranspose layers in Decoder. The number of latent space dimensions was z_dim = 256. The AE network was trained on CelebA images. I do not want to bore you with details of the codes for the creation of z-vectors consistent to the resulting elliptic conditions. It is all standard. The PCA-transformation can e.g. be taken from the sklearn-package.

I have applied a constant probability density to choose a random value within the allowed ranges for the component values of the aspired z-vectors in the PCA coordinate system. For the plots below I have used the most important 50 to 105 PCA components (out of 256). The plots include confidence ellipses on a level of σ = 2.2. I derived the confidence ellipses by directly evaluating the standard deviations of the transformed distribution data in all coordinate directions.

The first plot shows you such an ellipse for the coordinate plane corresponding to the first two, most important PCA components. The orange points mark 20 z-points defined by 20 randomly z-vectors fulfilling all elliptic conditions. The plot contains 120,000 z-points for images out of the 170,000 CelebA pictures used during training.

Generated statistical vectors in the PCA coordinate system

For elliptic contour lines see the last post before the present one in this series. The next plot shows the same generated 20 z-vectors for other component-combinations among the first 20 of the most important PCA-components. The plots contain a selection of 60,000 z-points.

The outer z-points points do not always indicate that we have elliptic contours in the denser core of the displayed 2-dimensional distributions. But see the last post for proofs that the inner core inside the red ellipse really displays elliptic contours. You see that all random vectors lie within the 2-σ-ellipses.

The next plot shows the generated z-vectors in the original coordinate system of the latent space. The component values were back-transformed from the PCA-system to the original coordinate system.

Generated statistical z-vectors after an inverse PCA transformation to the original coordinate system of the latent space

We get similar plots for other component pairs. And of course for other generated vectors.

Generated statistical z-vectors in the PCA coordinate system

Generated statistical z-vectors after an inverse PCA transformation to the original coordinate system of the latent space

Technically we have obviously achieved what we wanted: Our generated statistical vectors are distributed within the core of our multidimensional ellipsoid.

Note that this method fortunately works even when we use a limited number of the PCA components, only. This is due to intricate properties of a PCA transformation which guarantee that a back-transformation puts the resulting points close to the original ones even when we omit less important PCA components. I cannot discuss the math-details in this blog. You have to see scientific literature for this. An introduction is e.g. provided by https://arxiv.org/pdf/1404.1100.pdf.

For me this property of the PCA transformation was helpful when I ran into the resolution problem for a proper half-width of the Gaussians. Taking 256 components lead to errors as elliptic conditions for very narrow Gaussians were not properly defined and some of the created vectors left the allowed value ranges.

Resulting face images

Let us look at some results. First I want to remind you from where we started:

Failed trials with improper random z-vectors based on constant probability densities

A simple random generator used in the beginning was totally inapt to feed the AE’s Decoder with proper statistical z-vectors. And now – look at the following plots. They were produced for a varying number of PCA components between 50 and 120, 100000 statistically selected z-points within a 3 σ-level for the PCA-transformation and various factors 0.6 < fact < 0.8 used upon a half-width corresponding to a confidence level of 2.35 σ:

In some cases – for a higher number of PCA components – we even see smaller details of the face images and a reasonable transition to some kind of hairdo. Please remember that z_dim = 256 is a pretty low number for the latent space to cover the encoding of face details. And celebrities as covered by CelebA use make-up ….

In case you think the above result is not noteworthy: Please remember that we talk about a simple standard Autoencoder and not about a Variational Autoencoder and neither about a transformer based Autoencoder. No fancy additions to cost functions or special layers. And who ever has read the very instructive book of D. Foster on “Generative Deep Learning” (1st edition, O’Reilly) may compare his images to mine. And I have used a lower resolution of the original images than D. Foster. Just to motivate people to look a bit deeper into properties of data distributions in latent spaces.

Conclusion and outlook

We have come a lot closer to our objective of using a standard minimal Autoencoder for generative purposes. On our way, we got a much deeper understanding of the vector-distribution a trained AE creates in its latent space for human face images.

The method presented in this post to create reasonable statistical z-vectors still has its limits and there is a lot of open space for improvements. Attentive readers may e.g. ask: Why did he not use confidence ellipses directly? And why not the ellipses found in the original coordinate system of the latent space? And what about micro-correlations? And are there clusters for certain properties as the hair-color, sex, smiling, etc. in the multivariate z-point distribution in the AE’s latent space?

I will discuss these topics in further posts. In the meantime keep in mind that the basic point for turning a standard Autoencoder into a generative tool is to understand how it fills its latent space.

Note also that I myself have speculated in other posts of this blog that failures of using standard AEs for generative purposes may have their ultimate reason in the micro-structure of the z-point distribution. The present results render these previous ideas of mine plain wrong.

Links to previous posts of this series

Autoencoders and latent space fragmentation – IX – PCA transformation of the z-point distribution for CelebA

Autoencoders and latent space fragmentation – VIII – approximation of the latent vector distribution by a multivariate normal distribution and ellipses

Autoencoders and latent space fragmentation – VII – face images from statistical z-points within the latent space region of CelebA

Autoencoders and latent space fragmentation – VI – image creation from z-points along paths in selected coordinate planes of the latent space

Autoencoders and latent space fragmentation – V – reconstruction of human face images from simple statistical z-point-distributions?

Autoencoders and latent space fragmentation – IV – CelebA and statistical vector distributions in the surroundings of the latent space origin

Autoencoders and latent space fragmentation – III – correlations of latent vector components

Autoencoders and latent space fragmentation – II – number distributions of latent vector components

Autoencoders and latent space fragmentation – I – Encoder, Decoder, latent space

 

And before we forget it: Besides the Putler in the east there is also an extremist right-wing, semi-fascistic party in Germany on a record high support level in the population of 18%. This is a party which wants to stop all sanctions against the Russian aggressor in the ongoing war in Ukraine. You see the pattern behind this? This party is presently becoming bigger in number of supporters than the government leading social democrats. So, there is more at stake at present in Europe than the war in Ukraine. We need to defend our democracies with all the means of democracies. And its time to ask for more decisive legal action against a party which already is under observation of the German internal secret service.

 

Autoencoders and latent space fragmentation – IX – PCA transformation of the z-point distribution for CelebA

This series of posts is about standard convolutional Autoencoders [AEs]. We wish to use the creative ability of an AE’s Decoder for the creation of human face images. We trained a relatively simple example AE on the CelebA data set. For the generation of new human face images we wanted to feed the Decoder with randomly created z-vectors in the AE’s latent space. As arbitrary latent vectors did not deliver reasonable images, we had a look at properties of the z-point distribution created in the latent space after training. And we found the z-vectors with end-points within this particular region indeed gave us some first reasonable images.

But during the first posts we also had to learn that it requires substantial effort to produce “randomly” created z-vectors which point to the coherent and confined latent space region populated by z-points for CelebA images. In addition we found that we obviously must fulfill complex correlation conditions between the latent vector components. In the last posts we have, therefore, investigated the structure of the latent space region populated for CelebA images a bit more closely. See:

Autoencoders and latent space fragmentation – VIII – approximation of the latent vector distribution by a multivariate normal distribution and ellipses

Autoencoders and latent space fragmentation – VII – face images from statistical z-points within the latent space region of CelebA

This gave us a somewhat surprising insight:

For our special case of human face images the density distribution of the z-points in the multidimensional latent space roughly resembled a multivariate normal distribution. The variables of this distribution were, of course, the components of the latent z-vectors (reaching from the origin of the latent space coordinate system to the z-points). The number density distributions for the values of the z-vector components could very well be approximated by Gaussian functions. In addition we found strong linear correlations between the z-vector components. This was completely consistent with diagonally oriented elliptic contour lines of the number density distribution for pairs of z-vector components in the respective coordinate planes. The angles between the ellipses’ axes and the axes of the (orthogonal) coordinate system varied.

In this post we test my thesis of a multivariate normal distribution in a different and more complicated way. If the number density distribution of the z-points for CelebA really is close to a multivariate normal distribution then we would expect that the contour lines of the 2-dimensional number density function for coordinate planes still are ellipses after a PCA transformation. Note that the coordinate planes then are planes of a new coordinate system (with orthogonal axes) moved and rotated with respect to the original coordinate system. We call the transformed coordinate system the “PCA coordinate system“. (It is clear the vector components must consistently be transformed with respect to the new coordinate axes.)

This test is much harder because asymmetries, imperfections and deviations from a normal distribution will become clearly visible. Nevertheless we shall see that the z-point distribution decomposes roughly in uncorrelated Gaussian number density (or probability) functions for the (transformed) components of the z-vectors – as expected.

Note that number density distributions can be interpreted as probability distributions after a proper normalization. To understand the results and implications of this post some basic knowledge about multivariate normal probability density distributions in multidimensional spaces is required. Transformation properties of such distributions are important. In particular the effect of a PCA or SVD transformation, which diagonalizes the Pearson correlation matrix, on a multivariate normal distribution, should be familiar: In the moved and rotated coordinate system original linear correlations between vector components disappear. The coordinate axes of the transformed coordinate system get aligned to the eigenvectors (and main axes) of the probability density distribution. In addition elliptic contour lines prevail and the main axes of the ellipses get aligned with the axes of the PCA coordinate system.

For valuable information in previous posts see the link list a the bottom of this article.

Imperfections in the multivariate normal distribution and their consequences for PCA

In our case the latent space had 256 dimensions. The real number density functions for the values of the (256) latent vector components did not always show the full symmetry of their Gaussian fits. Deviations appeared near the center and at the flanks of the individual distributions. Still we got convincing overall ellipses in contour plots of the probability density for selected pairs of components. But there were also relatively many points which lay in regions outside the 2 to 3 sigma confidence ellipses for these 2-dimensional distributions – and the distribution of the points there seemed to violate the elliptic symmetry.

A perfect multivariate normal distribution (with only linear correlations between its variables) decomposes into (seemingly) uncorrelated normal distributions for the new variables, namely the latent vector components in the transformed coordinate system of the latent space. The coordinate transformation corresponds to a diagonalization of the Pearson correlation matrix via finding orthogonal eigenvectors. So we should not only get ellipses after the PCA transformation. The main axes of the resulting ellipses should also be aligned with the coordinate axes of the new translated and rotated PCA coordinate system. (This is a standard feature of “uncorrelated” Gaussians).

Note that the de-correlation is a pure coordinate effect which does not eliminate the dependencies of the original variables. The new coordinates and the respective variables do not have the same meaning as the old ones. We “only” change perspectives such that the mathematical description of the multivariate distribution gets simpler. However, the ratios of the axes of the new ellipses depend on the axis-ratios of the old ellipses in the original standard coordinate system of the latent space.

When we translate and rotate a coordinate system to diagonalize the Pearson matrix of an imperfect multivariate normal distribution the coordinate axes may afterward not fully align with the main axes of the distribution’s inner core – and then we might get clearly visible asymmetries in z-point projections to coordinate planes. Note that points outside the inner core have a relatively large impact on the PCA transformation and especially on the rotation of the new axes with respect to the old ones.

Reduction of outer z-point contributions

Outer z-points often correspond to CelebA images with strong variations in the background. As these z-points have a large distance from the center of the distribution they have a heavy impact on a PCA transformation to eigenvectors of the Pearson matrix. Therefore, I eliminated some outer points from the distribution. I did this by deleting points with coordinate values smaller or bigger than a symmetric threshold in the outer flanks of the 256 Gaussian distributions – e.g.:

z_j < mu_j – fact * FHWM and z_j > mu_j + fact * FHWM.

With FHWM meaning the full width at the half maximum and mu_j being the center of the approximate Gaussian for the j-th vector component of the z-vectors. I tried multiple values of fact between 1.7 and 1.25.

One has to be careful with such an elimination process. Even though we set our limits beyond the 2 σ-level of the individual Gaussians ahead of the transformation, a step-wise consecutive elimination for all components reduces the number of surviving vectors significantly for small values of fact. The plots below correspond to a value of fact = 1.7 (with one discussed exception). This reduced the number of available vectors from originally 170.000 used during the AE’s training to 160.000. From this distribution a random sub-selection of 80,000 z-points was taken to perform the PCA transformation. I call the resulting sample of z-points the “reduced distribution” below. The results did not change much for a sub-selection of more points. The second reduction saved me some CPU-time, however.

PCA transformation of the z-point distribution – explained variance and cumulative importance

Below you see the explained variance ratio of the first 40 and the cumulative importance of the first 120 main components after a PCA transformation of the reduced z-point distribution. (The PCA-algorithm was based on the SVD-algorithm, as provided by the sklearn-package.)

We see that we need around 120 PCA components to explain 80% of the variance of the original z-point data. The contribution of the first 15 components is significant, but it is NOT really dominant. Interesting is also the step-wise decline of the first 10 components in a not so smooth curve.

I have in addition checked that the normalized Pearson correlation coefficient matrix was perfectly diagonalized. All off-diagonal values were smaller than 2.e-7 (which is consistent with error propagation) and the diagonal elements were 1.0 with an accuracy better than 8 eight digits after the decimal point. As it should be.

Gaussians per PCA-vector component?

We expect Gaussian number density functions for each of the z-vector components after the PCA coordinate transformation. The following line plots show the number density distributions (colored line) and a related Gaussian fit (dashed lines) per named vector-components after PCA-transformation. The first plot gives an overview over 120 PCA components:

We see that all distributions look similar to Gaussians. In addition the center of the distributions for all components are very close to or coincide with the origin of the PCA coordinate system. This is something we would expect for an original multivariate normal distribution before the PCA transformation to a new moved and rotated coordinate system: An affine transformation between coordinate systems with orthogonal axes maps Gaussians to Gaussians.

Components 0 and 1:

Components 2 and 3:

Components 4 and 5:

Components 6 and 7:

Components 8 and 9:

We see from these plots that component 3 shows values at the distributions’s flanks well above the values of its Gaussian fit. This may lead to deformed ellipses. In addition component 7 shows a slight asymmetry – probably triggering deviations both at the center and outer regions. Similar effects can be seen for other higher components – but not so pronounced. The chosen sampling interval (0.5) in the new coordinates did smear out small asymmetric wiggles in all distributions.

Ellipses?

Calculating approximate contour lines is CPU intensive. On my presently available laptop I had to focus on some selected examples for pairs of components of z-vectors in the transformed coordinate system. Experiments showed that the most critical components with respect to asymmetries were 2, 3, 7, 8.

Let us first look at combinations of the first 9 PCA components (0) with other components in the range between the 10th and 120th PCA component. Just scroll down to see more images:

The fatter lines represent confidence ellipses derived both from correlation data, i.e. elements of the normalized correlation coefficient matrix, and properties of the Gaussian distributions. See the last blog for details on the method of getting confidence ellipses from data of a probability distribution.

Ellipses for density distributions in coordinate planes for pars of the most important PCA components

Before you think that everything is just perfect we should focus on the most important 10 PCA components and their mutual pair-wise density distributions. We expect trouble especially for combinations with the components 2, 3 and 7.

Component 0 vs other components < 10

We see already here that asymmetries in the density distributions which appear relatively small in the gaussian-like curves per component leave their imprint on the elliptic curves. The contour lines are not always centered with respect to the overall confidence ellipses.

Component 1 vs other components < 10

Component 2 vs other components < 10

The plot for components 2 and 3 was based on fact = 1.35 instead of fact = 1.7. See a section below for more information.

Component 3 vs other components < 10

Component 4 vs other components < 10

Component 5 vs other components < 10

Component 6 vs other components < 10

Component 7 vs other components < 10

Component 8 vs other components < 10

Component 9 vs other components < 10

Ellipses for other seected component pairs

Comments

The z-point distribution is rather close to a multivariate normal distribution, but it is not perfect. The PCA transformation revealed clearly that the center of the overall z-point distribution does not completely coincide with the centers of the individual density distributions for the z-vector components. And not all individual curves are fully symmetrical. Some plots show the expected ellipses, but not fully centered. We also see signs of non-linear correlations as not all ellipses show a complete alignment with the axes of the PCA coordinate system.

The impact of outer z-points becomes obvious when we compare plots for the component pair (2, 3) for different values of fact. The plots are for fact = 1.35, 1.45, 1.55, 1.7 and fact = 1.8 (in this order from left to right and downward). (Regarding z-point elimination the fact-values correspond to 122000, 138000, 149000, 159000 and 164000 remaining z-points.)

The flips in the left-right orientation between some of the plots can be ignored. They depend on random aspects of the transformations and plotting routines used.

We see that z-points (for some some strange images) which have a large distance from the center of the distribution have a major impact on the central density distribution. 10% of the outer points influence the orientation of the central ellipses by their coordinates – although these outer points are not part of the inner core of the distribution.

BUT: Overall we find the effect we wanted to see. The elliptic contours are clearly visible and most of them are aligned with the axes of the PCA coordinate system and the main axes of the confidence ellipses for the z-point distribution in the PCA coordinate system. The inner core is aligned with the axes of the coordinate system even for the critical PCA components 2 and 3, when we omit between 12% and 25% of the points (outside a 3 σ-level).

This means: The PCA transformation confirms that an inner core of the z-point distribution is well described by a multivariate normal distribution – with linear correlations between the number density distributions for various components.

This is an interesting finding by itself.

Conclusion

The last and the present post of this series have shown that a convolutional AE maps human face images of the CelebA data set to a multivariate normal distribution in its multidimensional latent space. Although this is interesting by itself we must not forget our ultimate goal – namely to generate random z-vectors which should deliver us reasonably human face images by the AE’s Decoder. But the results of our analysis provide solid criteria to generate such vectors fulfilling complex correlation conditions.

We can now define statistical generation methods which restrict the components of our aspired random z-vectors such that the resulting z-points lie within regions surrounded by confidence ellipses of the multivariate normal distribution. One such method is the topic of the next post.

Autoencoders and latent space fragmentation – X – a method to create suitable latent vectors for the generation of human face images

Links to other posts of this series

Autoencoders and latent space fragmentation – VIII – approximation of the latent vector distribution by a multivariate normal distribution and ellipses

Autoencoders and latent space fragmentation – VII – face images from statistical z-points within the latent space region of CelebA

Autoencoders and latent space fragmentation – VI – image creation from z-points along paths in selected coordinate planes of the latent space

Autoencoders and latent space fragmentation – V – reconstruction of human face images from simple statistical z-point-distributions?

Autoencoders and latent space fragmentation – IV – CelebA and statistical vector distributions in the surroundings of the latent space origin

Autoencoders and latent space fragmentation – III – correlations of latent vector components

Autoencoders and latent space fragmentation – II – number distributions of latent vector components

Autoencoders and latent space fragmentation – I – Encoder, Decoder, latent space

 

Autoencoders and latent space fragmentation – VIII – approximation of the latent vector distribution by a multivariate normal distribution and ellipses

This post series is about creative abilities of convolutional Autoencoders [AE] which have been trained on a set of human face images. The objectives of this series and its numerical experiments are:

  • We want to create images with human faces from statistical z-vectors and related z-points in the AE’s latent space [z-space or LS]. Image creation will be done with the help of the AE’s Decoder after a training on the CelebA dataset.
  • We work with a standard Autoencoder, only. I.e., we do NOT add any artificial layers and cost terms to the Autoencoder’s layer structure (as it is done e.g. in Variational Autoencoders).
  • We analyze the position, shape and internal structure of the multidimensional z-vector distribution created by the AE’s Encoder after training. We assume that generated statistical z-vectors must point to respective regions of the latent space to guarantee images with reasonable content.
  • We raise the question whether simple statistical generator algorithms are sufficient to cover these regions with statistical z-vectors.

Our numerical experiments gave us some indications that such an endeavor is indeed feasible. In addition the third objective may give us some insight into the rules a trained AE follows when it encodes information about human faces into vectors of its latent space.

We have already studied the “natural” z-vector distribution created by a convolutional Autoencoder for CelebA images after a thorough training. The related z-point distribution fortunately filled just one confined and coherent off-center region of the AE’s latent space. Our experiments have furthermore shown that we must indeed restrict the statistical z-vector creation such that the vectors point to this particular region. Otherwise we will not get reasonable images. For details see the previous posts.

Autoencoders and latent space fragmentation – VII – face images from statistical z-points within the latent space region of CelebA
Autoencoders and latent space fragmentation – VI – image creation from z-points along paths in selected coordinate planes of the latent space
Autoencoders and latent space fragmentation – V – reconstruction of human face images from simple statistical z-point-distributions?
Autoencoders and latent space fragmentation – IV – CelebA and statistical vector distributions in the surroundings of the latent space origin
Autoencoders and latent space fragmentation – III – correlations of latent vector components
Autoencoders and latent space fragmentation – II – number distributions of latent vector components
Autoencoders and latent space fragmentation – I – Encoder, Decoder, latent space

The frustrating point so far was that simple methods for creating statistical vectors fail to put the end-points of the z-vectors into the relevant latent space region. In particular methods based on constant probability distributions within a common value interval for all z-vector components are doomed to miss the interesting region due to intricate mathematical reasons.

Afterward we tried to restrict the component values of test vectors to intervals defined by the shape of the number distribution for the values of each component of the CelebA related z-vectors. Such a distribution is nothing else than a one-dimensional probability density function for our special set of encoded CelebA samples: The function describes the probability that a component of a z-vector for human face images gets a value within a certain small value range. The probability distributions for all z-vector components were bell shaped and showed clear transitions to flat wings with very low values. See the plots below. This allowed us to define a value range

d_j_l   <   x_j   <   d_j_h

for each vector component x_j.

But keeping statistical values per component within the identified respective interval was not a sufficient restriction. We saw this clearly in the last post from significant irregular fluctuations in the reconstructed images. Obviously the components of statistically generated z-vectors must in addition fulfill correlation conditions.

The questions which I want to answer in this post are:

  • Can we approximate the 1-dimensional probability density functions for the z-vector components by some simple and common mathematical function?
  • What kind of correlations do we find between the components of the z-vectors encoding the information of human face images?
  • Can we derive some mathematical description of the multivariate z-vector distribution created by convolutional AEs for human face images in the AE’s multidimensional latent space?

Correlations are to be expected …

Please note: We deal with a multidimensional problem. A single latent vector encodes information about a human face image via all of its component values and by relations between these values. Regarding the purpose and the task an AE has to fulfill, it would be naive to assume that the components of our multi-dimensional z-vectors were independently organized. A z-vector encodes information for a convolutional Decoder to combine patterns detected by the Encoder and represented in neural (feature) maps of the networks to create an image. This is a subtle business. Just think about what you do when you draw a sketch of a human face. There are a lot of rules you follow.

When you think about the properties of basic feature patterns in a human face you would certainly assume that the pixel data of a corresponding image show strong correlations. This is among other things due to obvious symmetries – not excluding fluctuations of basic parameters describing human face features. But a nose tends to be at a position below the eyes and at a mid-distance of the eyes. In additions fluctuations of face features would on average respect certain limits given by natural proportions of a face. It would therefore be unreasonable to assume that the input for a Decoder to create a superposition of elementary patterns consists of un-correlated data. Instead the patterns in the original data should not only lead to well adjusted weights in the convolutional networks’ feature maps, but also to well regulated structural elements in the data distribution in the target space of the information encoding, namely in the latent space.

If the relations of the vector components were of a complex, highly non-linear kind and involved many dimensions at the same time we might be lost. But the results we have gained so far indicate a proper common structure of at least the density function for the individual components. This gives us some hope that the multidimensional problem somehow involves well defined 1-dimensional constituents. Whether this a sign that the multidimensional structure of the z-vector distribution can be decomposed into low-dimensional relations remains to be seen.

Observations regarding the z-vector distribution created by convolutional Autoencoders for human face images

Coordinate values of the z-points are identical to z-vector component values when we fix the end of each vector to the origin of the latent space coordinate system. The z-vector distribution thus directly corresponds to a z-point density distribution in the orthogonal coordinate system of the AE’s multi-dimensional LS. We have already made three interesting observations regarding these distributions:

  • The individual probability density function for a selected component of the latent vectors has a bell-shaped form. One , therefore, is tempted to think of a Gaussian function. This would indicate a possible normal distribution for the coordinate values of the z-points along each of the selected coordinate axes.
    Note: This does not exclude that the probability distributions for the components are correlated in some complex way.
  • When we plotted the projection of the z-point distribution onto 2-dimensional coordinate planes (for selected pairs of coordinate axes) then almost all of the resulting 2-dimensional density distributions seemed to have a defined core with an ellipsoidal form of its boundary.
  • For certain component- or axis-pairs the main axes of the apparent ellipses for pair-wise density function appeared rotated against the coordinate axes. The elongated regular and more or less symmetric forms showed a diagonal orientation (with different angles). This alone signals a strong correlation between related two vector components. Indeed we found high values for certain elements of the matrix of normalized Pearson correlation coefficients for the multi-dimensional distribution of z-vector component values.

These observations are not unrelated; they indicate a clear pattern of dependencies and correlations of the distributions for the variables in place. Regarding the data basis we have to keep five things in mind:

  • We treat the z-point distribution for CelebA images as a multi-dimensional probability density distribution. During the analysis we look in particular at 2-dimensional projections of this distribution onto planes spanned by a selected pair of orthogonal axes of the LS coordinate system. We also consider the one-dimensional value distributions for z-vector components. In this sense we regard the z-vector components as logically separate variables.
  • The data used are numbers of z-points counted in finite 1d-intervals, 2d-rectangles or multidimensional cuboids. We fit idealized functions to the respective discrete bar plots. Even if there is a good 1d-fit fluctuations may especially get visible in multidimensional plots for correlated data. A related probability density requires a normalization. We drop the resulting constant factors in the qualitative discussions below.
  • Statistical (un-)correlation of statistical variable distributions must NOT to be confused with underlying variable (in-) dependency. Linear correlations can be reduced to zero by coordinate transformations without eliminating the original variable dependencies.
  • Pearson correlation coefficients are sensitive to linear elements in the relations of logically separate variable distributions. They can not fully cover non-linear distribution relations or covered variable dependencies.
  • A transformation to a local coordinate system whose axes are aligned to the so called main axes of the multidimensional distributions does not remove the original data relations – but there may exist a coordinate system in which the distribution data can be described in a simple, factorized form corresponding to a composition of seemingly un-correlated data distributions.

Anyway – by discussing density distributions we work on overall and large scale average relations between statistical value distributions for our variables, namely the z-vector components. We do not cover local micro-relations that may be in place in addition.

The relation of ellipses with Gaussian probability densities

Probability density functions for two logically separate, but maybe not un-correlated variables have to be multiplied. In our case this reflects the following point: First we determine the probability that the value of component x_i lies in a certain (infinitesimal) interval and then we determine the probability that (for the given value of x_i) the component x_j falls into another value range. The distributions for a specific variable can include variable relations and thus the probability density g(x_j) can include a dependency g(x_j(x_i)).

In the case of uncorrelated normal distributions per coordinate we can just multiply the individual Gaussians g(x_i) * g(x_j). Due to the quadratic terms in the exponent of the Gaussians we then get a sum of quadratic expressions in the common exponent, having the form fac1 * (x_i-mu_i)**2 + fac2 * (x_j-mu_j)**2.

By setting this expression to a constant value we get contour lines of the probability density distribution for the (x_i, x_j)-distribution. Quadratic sums correspond to the definition of an ellipse having main axes which are aligned with the x_i- and x_j-axes of the coordinate system. Thus the contour lines of a 2-dimensional distribution composed of un-correlated Gaussians are ellipses having an orientation aligned with the coordinate axes.

This was for un-correlated density-distributions of two vector components. Mathematically a linear correlation between a pair of Gaussians-distributions corresponds to an affine transformation of the contour-ellipses. The transformation can be expressed by a defined sequence of matrix operations describing a translation, rotations (in a defined order) and a dilation.

This means: The contour lines for a 2-dimensional probability density composed of linearly correlated Gaussians are still ellipses. But these ellipses will appear to be shifted, rotated and stretched along the main axes in comparison with their originally un-correlated Gaussian counterparts. The angle of rotation depends on details of the correlation function and the original standard deviations. The Pearson correlation matrix for linearly correlated distributions is a positive-definite one and, of course, shows off-diagonal elements different from zero. This result can be extended to multivariate normal distributions in spaces with many dimensions and related affine transformations of the coordinate system.

A multivariate normal distribution with linear correlations between the Gaussians results in elliptic contour lines for pair-wise density distributions in the respective 2D-coordinate planes of an orthogonal coordinate system. When we define the contours via multiples of the standard deviations of the underlying Gaussian functions we arrive at so called confidence ellipses.

A really nice mathematical aspect is that the basic parameters of the confidence ellipses can be derived from the normalized correlation coefficients of the Pearson matrix of the multivariate probability distribution. I will come back to this point in forthcoming posts in more detail. For now we just need to know that a multidimensional probability density comes along with confidence ellipses which can be calculated with the help of Pearson correlation coefficients.

Before we go on a word of caution: For a general multi-variate distribution it is not at all clear that it should decompose into a factorized form. However, for a multivariate normal distribution with un-correlated or only linearly correlated components this is by definition different. In this case a transformation to a coordinate system can be found which leads to a complete decomposition into a product of (seemingly) un-correlated Gaussians per component. The latter point lies at the center of PCA and SVD algorithms, which diagonalize the Pearson correlation matrix.

Do we really have Gaussian probability distributions for the individual z-vector-components?

After this short tour into the world of (multi-variate) normal distributions, Gaussian functions and related ellipses we are a bit better equipped to understand the density distributions in the latent space of our Autoencoders for human face images.

Let me remind you about the shapes of the number distribution for our concrete z-vector components resulting for for CelebA face images. The first plot shows the number densities on sampling intervals of width 0.25 for selected vector components resulting for case I of our experiments. The second plot shows the number densities for the values of selected components of case II.

Ok, these curves do resemble Gaussians and some fluctuations are normal. But can we prove the Gaussian properties of the curves a bit better?

Well, for case II I have drawn the best fits by Gaussian functions with the help of SciPy’s optimize.curve_fit() for 3 and yet another 4 selected components of the latent vectors and the respective number distribution curves. The dashed lines show the approximations by Gaussian functions:

The selected components are part of the list of around 20 dominant component distributions – due to their relatively large standard deviations. But the Gaussian form is consistently found for all components (with some small deviations regarding the symmetry of the curves).

So all in all it looks like as if our convolutional AE has indeed created a multivariate normal z-point distribution in the latent space. As said: This does not exclude correlations …

Pairwise linear correlations of the (normal) probability distributions for the latent vector components?

Now we are a bit bold – and assume the best case for us: Could the approxiate Gaussians distributions for the component values be pair-wise and linearly correlated? What would be a clear indication of a pair-wise linear correlation of our component distributions?

Well, we should find an elliptic form of contour lines in the 2-dimensional distribution for the component pair in the respective coordinate plane of the basic orthogonal LS coordinate system. This imposes quite strong symmetry conditions on the contour lines. The ellipses can be shifted and rotated – but they should remain being ellipses. If non-linear contributions to the correlation had a significant impact this would not be the case.

Practically it is not trivial to prove that we have approximately rotated ellipses in 2 dimensions. Satter plos alone do not help: Ellipses fit a lot of plotted distributions of discrete data points quite well. We really need to count number densities to get reliable contour lines. The following plots show such contour lines based on number sampling in rectangles and local smoothing operations with the help of scipy.stats.gaussian_kde().

The fat red and dark orange lines show corresponding confidence ellipses derived from the original CelebA distribution. See below for some remarks on confidence ellipses.

The contours are basically of elliptic shape although they do not show the complete symmetry expected for pure and linearly dependent Gaussian distributions. But overall the confidence ellipses fit quite well into the general form and orientation of the distributions. We also see that for higher σ-levels the coincidence with nearby contours is quite good. The wiggles in the contour change with the z-vector selection a bit.

We conclude that our basic impression regarding an elliptic shape of the z-point distributions is basically consistent with only linearly correlated Gaussian probability density distributions for the component values of the latent vectors.

Approximation of the core of the multivariate z-point distribution by confidence ellipses for component pairs

Above I referred to the boundary of a core of the probability density for two selected vector components. But how would we define the “boundary” of a continuous distribution in the coordinate planes? Answer: As we like – but based on the decline of the approximate Gaussian curves.

We can e.g. pick two times the half-width in each direction or we can use contours defined by confidence levels.
For 2 ≤ fact * σ ≤ 3 we saw already that the contour lines could well be fitted by confidence ellipses. A 3-sigma level covers around 97% of all data points or more. A 2 sigma-level ellipse encircles between 70% and 90% of all data points, depending on the eccentricity of the ellipse. Note that the numbers are smaller for ellipses than for rectangles. I.e. the standard 68-95-99.7 rule does not apply.

The plots below give you an impression of how well ellipses for a -confidence level approximate the core of the CelebA distribution in selected 2D coordinate planes of the latent space:

Each of the sub-plots was based on 10,000 statistically selected vectors of the 170,000 available in my test runs. This is a relative low number. Therefore, for a certain diameter of the points in the scatter plot only the inner core appears to be densely populated. The next plots shows the results for a 3 σ-level of the ellipse – but this time for 50,000 vectors. With more vectors we could visually fill the outer regions of the core.

The orange points mark the center of the multidimensional distributions derived from the one-dimensional distribution curves for the components. We see that it does not always appear to be optimally centered. There are multiple reasons: Our functions are not fully symmetric as ideal Gaussians. And equally important: The accuracy of the position depends on the sampling resolution which was coarse. Outliers of the distribution do have an impact.

And how would we explain the appearance of Gaussians and ellipses?

This all looks quite good, despite some notable deviations regarding symmetry and maxima. Gaussians fit at least most of the important probability density curves very well, though not by a 100%. The appearance of an elliptic shape of the inner core of the distribution and the appearance of overall elliptic contour curves can be explained by linear correlations of the Gaussian distributions for the components.

The appearance of normal distributions per component and basically linear correlations is something that really should be explained. I mean, dwell a bit on what we have found:

A convolutional Autoencoder network with more than 10 million adjustable parameters encoded information about human face images in the form of a roughly multivariate normal distribution of z-points in its latent space – with basically linear correlations between the Gaussian curves describing the probability densities functions for the component values of the z-vectors.

I find this astonishing and not at all self-evident. It is one of the most simple solutions for a multidimensional situation one can imagine. The following questions automatically came to my mind:

Does such a result only appear for training images of defined objects with some Gaussian variation in their features? Are the normal distributions a reflection of variations of relevant features in the original data?
Is this a typical result for (convolutional) AEs? How does it depend on the dimensionality of the latent space? Does it automatically come with a large number of z-space dimensions? Is it an efficient way to encode feature differences in the latent space, which (convolutional) AEs in general tend to use due to their structure?

Do I personally have a convincing explanation? No. Especially not, as the data shown above stem from convolutional neural networks [CNNs] without any batch-normalization layers.

A first idea would be that the dominant features of a human face themselves show variations described by Gaussian normal distributions already in the original data and that convolutional filtering does not destroy such distributions during optimization. A problem of this idea lies in the (non-) linear activation functions used at the nodes of the neural maps. Though ReLU, Leaky ReLU and SeLU contain linear parts.

The other problem is the linear form of the correlations. This is a rather simple kind of correlations. But why should an AE choose this simple form into its mapping of image information to latent space vectors after training?

How to generate statistical vectors for the creation of human face images?

The positive message which comes with the above results is that our problem of how to create proper statistical z-vectors decomposes into a sequence of two-dimensional problems. We can use the data of the ellipses appearing in the density-distributions for pairs of vector components to confine the components of statistically generated z-vectors to the relevant region in the latent space. All ellipses together restrict the component values in a well defined form. In the next post I will shortly outline some methods of how we can use the information contained in the ellipses with available algorithms.

Conclusion

In this post we have seen that for the case of a convolutional Autoencoder trained on CelebA human face images the latent vector distributions showed some remarkable properties:

The probability density functions for all component values can roughly be approximated by Gaussian functions. The components appear to be pairwise linearly correlated – at least to first order analysis. This automatically implies elliptic contour curves for the pairwise number density functions of coordinate values. Such contour curves were indeed found with first order accuracy. The core of the probability density for the z-points in the latent space could therefore be approximated by confidence ellipses for a σ-level above σ = 2.5.
The elliptic conditions correspond to a multivariate normal distribution with linear correlations of the variables.

Before we get to enthusiastic about these findings we should be careful and await a further test. All statements refer to a first order approximations. A real multivariate normal distribution would decompose into un-correlated Gaussians and 2D-ellipses of probability densities of component pairs after a PCA transformation.

In the next post

Autoencoders and latent space fragmentation – IX – PCA transformation of the z-point distribution for CelebA

I shall present the results of a PCA analysis. In later posts I will introduce a related method to restrict the components of statistical vectors to the relevant region in the latent space of our Autoencoder.

Links and literature

On first sight my short description of the relation between multivariate Gaussian normal distributions and ellipses as the contour lines for the projected density distributions on coordinate planes may appear plausible. But in the general multi-dimensional case the question of linear correlations requires some more math than indicated. For details I just refer to some articles on the Internet – but any good book on multivariate analysis will give you the relevant information
https://de.wikipedia.org/ wiki/ Multivariate_ Normalverteilung
https://de.wikipedia.org/ wiki/ Mehrdimensionale_ Normalverteilung
http:// www.mi.uni-koeln.de/ ~jeisenbe/ Vortrag2.pdf
https://methodenlehre.uni-mainz.de/ files/ 2019/06/ Multivariate-Distanz-Normalverteilung-MDC-Bayes.pdf
https://en.wikipedia.org/ wiki/ Multivariate_ normal_ distribution
https://en.wikipedia.org/ wiki/ Confidence_region
https://users.cs.utah.edu/ ~tch/ CS6640F2020/ resources/ How to draw a covariance error ellipse.pdf
https://biotoolbox.binghamton.edu/ Multivariate Methods/ Multivariate Tools and Background/ pdf files/ MTB%20070.pdf

Regarding the intimate relation between the ellipses’ main axes to normalized Pearson correlation coefficients I also refer to
https://carstenschelp.github.io/ 2018/09/14/ Plot_ Confidence_ Ellipse_ 001.html
I am very grateful that the author Carsten Schelp saved me a lot of time when trying to find a way to program a solution for confidence ellipses. Thank you, Mr. Schelp for the great work.