A simple CNN for the MNIST dataset – V – about the difference of activation patterns and features

In my last article of my introductory series on “Convolutional Neural Networks” [CNNs] I described how we can visualize the output of different maps at convolutional (or pooling) layers of a CNN.

A simple CNN for the MNIST dataset – IV – Visualizing the activation output of convolutional layers and maps
A simple CNN for the MNIST dataset – III – inclusion of a learning-rate scheduler, momentum and a L2-regularizer
A simple CNN for the MNIST datasets – II – building the CNN with Keras and a first test
A simple CNN for the MNIST datasets – I – CNN basics

We are now well equipped to look a bit closer at the maps of a trained CNN. The output of the last convolutional layer is of course of special interest: It is fed (in the form of a flattened input vector) into the MLP-part of the CNN for a classification analysis. As an MLP detects “patterns” the question arises whether we actually can see common “patterns” in the visualized maps of different images belonging to the same class. In our case we shall have a look at the maps of different MNIST images of a handwritten “4”.

Note for my readers, 20.08.2020:
This article has recently been revised and completely rewritten. It required a much more careful description of what we mean by “patterns” and “features” – and what we can say about them when looking at images of activation outputs on higher convolutional layers. I also postponed a thorough “philosophical” argumentation against a humanized usage of the term “features” to a later article in this series.


We saw already in the last article that the images of maps get more and more abstract when we move to higher convolutional layers – i.e. layers deeper inside a CNN. At the same time we loose resolution due to intermediate pooling operations. It is quite obvious that we cannot see much of any original “features” of a handwritten “4” any longer in a (3×3)-map, whose values are produced by a sequence of complex transformation operations.

Nevertheless people talk about “feature detection” performed by CNNs – and they refer to “features” in a very concrete and descriptive way (e.g. “eyes”, “spectacles”, “bows”). How can this be? What is the connection of abstract activation patterns in low resolution maps to original “features” of an image? What is meant when CNN experts claim that neurons of higher CNN layers are allegedly able to “detect features”?

We cannot give a full answer, yet. We still need some more Python programs tools. But, wat we are going to do in this article are three things:

  1. Objective 1: I will try to describe the assumed relation between maps and “features”. To start with I shall make a clear distinction between “feature” patterns in input images and patterns in and across the maps of convolutional layers. The rest of the discussion will remain a bit theoretical; but it will use the fact that convolutions at higher layers combine filtered results in specific ways to create new maps. For the time being we cannot do more. We shall actually look at visualizations of “features” in forthcoming articles of this series. Promised.
  2. Objective 2: We follow three different input images, each representing a “4”, as they get processed from one convolutional layer to the next convolutional layer of our CNN. We shall compare the resulting outputs of all feature maps at each convolutional layer.
  3. Objective 3: We try to identify common “patterns” for our different “4” images across the maps of the highest convolutional layer.

We shall visualize each “map” by an image – reflecting the values calculated by the CNN-filters for all points in each map. Note that an individual value at a map point results from adding up many weighted values provided by the maps of lower layers and feeding the result into an activation function. We speak of “activation” values or “map activations”. So our 2-nd objective is to follow the map activations of an input image up to the highest convolutional layer. An interesting question will be if the chain of complex transformation operations leads to visually detectable similarities across the map outputs for the different images of a “4”.

The eventual classification of a CNN is done by its embedded MLP which analyzes information collected at the last convolutional layer. Regarding this input to the MLP we can make the following statements:

The convolutions and pooling operations project information of relatively large parts of the original image into a representation space of very low dimensionality. Each map on the third layer provides a 3×3 value tensor, only. However, we combine the points of all (128) maps together in a flattened input vector to the MLP. This input vector consists of more nodes than the original image itself.

Thus the sequence of convolutional and pooling layers in the end transforms the original images into another representation space of somewhat higher dimensionality (9×128 vs. 28×28). This transformation is associated with the hope that in the new representation space a MLP may find patterns which allow for a better classification of the original images than a direct analysis of the image data. This explains objective 3: We try to play the MLPs role by literally looking at the eventual map activations. We try to find out which patterns are representative for a “4” by comparing the activations of different “4” images of the MNIST dataset.

Enumbering the layers

To distinguish a higher Convolutional [Conv] or Pooling [Pool] layer from a lower one we give them a number “Conv_N” or “Pool_N”.

Our CNN has a sequence of

  • Conv_1 (32 26×26 maps filtering the input image),
  • Pool_1 (32 13×13 maps with half the resolution due to max-pooling),
  • Conv_2 (64 11×11 maps filtering combined maps of Pool_1),
  • Pool_2 (64 5×5 maps with half the resolution due to max-pooling),
  • Conv_3 (128 3×3 maps filtering combined maps of Pool_2).

Patterns in maps?

We have seen already in the last article that the “patterns” which are displayed in a map of a higher layer Conv_N, with N ≥ 2, are rather abstract ones. The images of the maps at Conv_3 do not reflect figurative elements or geometrical patterns of the input images any more – at least not in a directly visible way. It does not help that the activations are probably triggered by some characteristic pixel patterns in the original images.

The convolutions and the pooling operation transform the original image information into more and more abstract representation spaces of shrinking dimensionality and resolution. This is due to the fact that the activation of a point in a map on a layer Conv_(N+1) results

  • from a specific combination of multiple maps of a layer Conv_N or Pool_N
  • and from a loss of resolution due to intermediate pooling.

It is not possible to directly guess in what way active points or activated areas within
a certain map at the third convolutional layer relate to or how they depend on “original and specific patterns in the input image”. If you do not believe me: Well, just look at the maps of the 3rd convolutional layer presented in the last article and tell me: What patterns in the initial image did these maps react to? Without some sophisticated numerical experiments you won’t be able to figure that out.

Patterns in the input image vs. patterns within and across maps

The above remarks indicate already that “patterns” may occur at different levels of consideration and abstraction. We talk about patterns in the input image and patterns within as well as across the maps of convolutional (or pooling) layers. To avoid confusion I already now want to make the following distinction:

  • (Original) input patterns [OIP]: When I speak of (original) “input patterns” I mean patterns or figurative elements in the input image. In more mathematical terms I mean patterns within the input image which correspond to a kind of fixed and strong correlation between the values of pixels distributed over a sufficiently well defined geometrical area with a certain shape. Examples could be line-like elements, bow segments, two connected circles or combined rectangles. But OIPs may be of a much more complex and abstract kind and consist of strange sub-features – and they may not reflect a real world entity or a combination of such entities. An OIP may reside at one or multiple locations in different input images.
  • Filter correlation patterns [FCP]: A CNN produces maps by filtering input data (Conv level 1) or by filtering maps of a lower layer and combining the results. By doing so a higher layer may detect patterns in the filter results of a lower layer. I call a pattern across the maps of a convolutional or pooling layer Conv_N or Pool_N as seen by Conv_(N+1) a FCP.
    Note: Because a 3×3 filter for a map of Conv_(N+1) has fixed parameters per map of the previous layer Conv_N or Pool_N, it combines multiple maps (filters) of Conv_N in a specific, unique way.

Anybody who ever worked with image processing and filters knows that combining basic filters may lead to the display of weirdly looking, combined information residing in complex regions on the original image. E.g., a certain combination of filters may emphasize diagonal lines or bows with some distance in between and suppress all other features. Therefore, it is at least plausible that a map of a higher convolutional layer can be translated back to an OIP. Meaning:

A high activation of certain or multiple points inside a map on Conv_3 may reflect some typical OIP pattern in the input image.

But: At the moment we have no direct proof for such an idea. And it is not at all obvious what kind of OIP pattern this may be for a distinct map – and whether it can directly be described in terms of basic geometrical elements of a figurative number representation in the MNIST case. By just looking at the maps of a layer and their activated points we do not get any clue about this.

If, however, activated maps somehow really correspond to OIPs then a FCP over multiple maps may be associated with a combination of distinct OIPs in an input image.

What are “features” then?

In many textbooks maps are also called “feature maps“. As far I understand it the authors call a “feature” what I called an OIP above. By talking about a “feature” the authors most often refer to a pattern which a CNN somehow detects or identifies in the input images.

Typical examples of “features” text-book authors often discuss and even use in illustrations are very concrete: ears, eyes, feathers, wings, a mustache, leaves, wheels, sun-glasses … I.e., a lot of authors typically name features which human beings identify as physical entities or as entities, for which we have clear conceptual ideas in our mind. I think such examples trigger ideas about CNNs which are too far-fetched and which “humanize” stupid algorithmic processes.

The arguments in favor of the detection of features in the sense of conceptual entities are typically a bit nebulous – to say the least. E.g. in a relatively new book on “Generative Deep Learning” you see a series of CNN neuron layers associated with rather dubious and unclear images of triangles etc. and at the last convolutional layer we suddenly see pretty clear sketches of a mustache, a certain hairdress, eyes, lips, a shirt, an ear .. “. The related text goes like follows (I retranslated the text from the German version of the book): “Layer 1 consists of neurons which activate themselves stronger, when they recognize certain elementary and basic features in the input image, e.g. borders. The output of these neurons is then forwarded to the neurons of layer 2 which can use this information to detect more complex features – and so on across the following layers.” Yeah, “neurons activate themselves” as they “recognize” features – and suddenly the neurons at a high enough layer see a “spectacle”. 🙁

I think it would probably be more correct to say the following:

The activation of a map of a high convolutional layer may indicate the appearance of some kind of (complex) pattern or a sequence of patterns within an input image, for which a specific filter combination produces relatively high values in a low dimensional output space.

Note: At our level of analyzing CNNs even this carefully formulated idea is speculation. Which we will have to prove somehow … Where we stand right now, we are unfortunately not yet ready to identify OIPs or repeated OIP sequences associated with maps. This will be the topic of forthcoming articles.

It is indeed an interesting question whether a trained CNN “detects” patterns in the sense of entities with an underlying “concept”. I would say: Certainly not. At least not pure CNNs. I think, we should be very careful with the use of the term “feature”. Based on the filtering convolutions perform we might say:

A “feature” (hopefully) is a pattern in the sense of defined geometrical pixel correlation in an image.

Not more, not less. Such a “feature” may or may not correspond to entities, which a human being could identify and for which he or she has a concept for. A feature is just a pixel correlation whose appearance triggers output neurons in high level maps.

By the way there are 2 more points regarding the idea of feature detection:

  • A feature or OIP may be located at different places in different images of something like a “5”. Due to different sizes of the depicted “5” and translational effects. So keep in mind that if maps do indeed relate to features it has to be explained how convolutional filtering can account for any translational invariance of the “detection” of a pattern in an image.
  • The concrete examples given for “features” by many authors imply that the features are more or less the same for two differently trained CNNs. Well, regarding the point that training corresponds to finding a minimum on a rather complex multidimensional hyperplane this raises the question how well defined such a (global) minimum really is and whether it or other valid side minima are approached.

Keep these points in mind until we come back to related experiments in further articles.

From “features” to FCPs on the last Conv-layer?

However and independent of how a CNN really reacts to OIPs or “features”, we should not forget the following:
In the end a CNN – more precisely its embedded MLP – reacts to FCPs on the last convolutional level. In our CNN an FCP on the third convolutional layer with specific active points across 128 (3×3)-maps obviously can obviously tell the MLP something about the class an input image belongs to: We have proven already that the MLP part of our simple CNN guesses the class the original image belongs to with a surprisingly high accuracy. And by construction it obviously does so by just analyzing the 128 (3×3)-activation values of the third layer – arranged into a flattened vector.

From a classification point of view it, therefore, seems to be legitimate to look out for any FCP across the maps on Conv_3. As we can visualize the maps it is reasonable to literally look for common activation patterns which different images of handwritten “4”s may trigger on the maps of the last convolutional level. The basic idea behind this experimental step is:

OIPs which are typical for images of a “4” trigger and activate certain maps or points within certain maps. Across all maps we then may see a characteristic FCP for a “4”, which not only a MLP but also we intelligent humans could identify.

Or: Multiple characteristic features in images of a “4” may trigger characteristic FCPs which in turn can be used indicators of a class an image belongs to by an MLP. Well, let us see how far we get with this kind of theory.

Levels of “abstractions”

Let us take a MNIST image which represents something which a European would consider to be a clear representation of a “4”.

In the second image I used the “jet”-color map; i.e. dark blue indicates a low intensity value while colors from light blue to green to yellow and red indicate growing intensity values.

The first conv2D-layer (“Conv2d_1”) produces the following 32 maps of my chosen “4”-image after training:

We see that the filters, which were established during training emphasize general contours but also focus on certain image regions. However, the original “4” is still clearly visible on very many maps as the convolution does not yet reduce resolution too much.

By the way: When looking at the maps the first time I found it surprising that the application of a simple linear 3×3 filter with stride 1 could emphasize an overall oval region and suppress the pixels which formed the “4” inside of this region. A closer look revealed however that the oval region existed already in the original image data. It was emphasized by an inversion of the pixel values …

The second Conv2D-layer already combines information of larger areas of the image – as a max (!) pooling layer was applied before. We loose resolution here. But there is a gain, too: the next convolution can filter (already filtered) information over larger areas of the original image.

But note: In other types of more advanced and modern CNNs pooling only is involved after two or more successive convolutions have happened. The direct succession of convolutions corresponds to a direct and unique combination of filters at the same level of resolution.

The 2nd convolution
As we use 64 convolutional maps on the 2nd layer level we allow for a multitude of different new convolutions. It is to be understood that each new map at the 2nd cConv layer is the result of a special unique combination of filtered information of all 32 previous maps (of Pool_1). Each of the previous 32 maps contributes through a specific unique filter and respective convolution operation to a single specific map at layer 2. Remember that we get 3×3 x 32 x 64 parameters for connecting the maps of Pool_1 to maps of Conv_2. It is this unique combination of already filtered results which enriches the analysis of the original image for more complex patterns than just the ones emphasized by the first convolutional filters.

As the max-condition of the pooling layer was applied first and because larger areas are now analyzed we are not too astonished to see that the filters dissolve the original “4”-shape and indicate more general geometrical patterns – which actually reflect specific correlations of map patterns on layer Conv_1.

I find it interesting that our “4” triggers more horizontally activations within some maps on this already abstract level than vertical ones. One should not confuse these patterns with horizontal patterns in the original image. The relation of original patterns with these activations is already much more complex.

The third convolutional layer applies filters which now cover almost the full original image and combine and mix at the same time information from the already rather abstract results of layer 2 – and of all the 64 maps there in parallel.

We again see a dominance of horizontal patterns. We see clearly that on this level any reference to something like an arrangement of parallel vertical lines crossed by a horizontal line is completely lost. Instead the CNN has transformed the original distribution of black (dark grey) pixels into multiple abstract configuration spaces with 2 axes, which only coarsely reflecting the original image area – namely by 3×3 maps; i.e. spaces with a very poor resolution.

What we see here are “correlations” of filtered and transformed original pixel clusters over relatively large areas. But no constructive concept of certain line arrangements.

Now, if this were the level of “FCP-patterns” which the MLP-part of the CNN uses to determine that we have a “4” then we would bet that such abstract patterns (active points on 9×9 grids) appear in a similar way on the maps of the 3rd Conv layer for other MNIST images of a “4”, too.

Well, how similar do different map representations of “4”s look like on the 3rd Conv2D-layer?

What makes a four a four in the eyes of the CNN?

The last question corresponds to the question of what activation outputs of “4”s really have in common. Let us take 3 different images of a “4”:

The same with the “jet”-color-map:


Already with our eyes we see that there are similarities but also quite a lot of differences.

Different “4”-representations on the 2nd Conv-layer

Below we see comparison of the 64 maps on the 2nd Conv-layer for our three “4”-images.

If you move your head backwards and ignore details you see that certain maps are not filled in all three map-pictures. Unfortunately, this is no common feature of “4”-representations. Below you see images of the activation of a “1” and a “2”. There the same maps are not activated at all.

We also see that on this level it is still important which points within a map are activated – and not which map on average. The original shape of the underlying number is reflected in the maps’ activations.

Now, regarding the “4”-representations you may say: Well, I still recognize some common line patterns – e.g. parallel lines in a certain 75 degree angle on the 11×11 grids. Yes, but these lines are almost dissolved by the next pooling step:

Consider in addition that the next (3rd) convolution combines 3×3-data of all of the displayed 5×5-maps. Then, probably, we can hardly speak of a concept of abstract line configurations any more …

“4”-representations on the third Conv-layer

Below you find the activation outputs on the 3rd Conv2D-layer for our three different “4”-images:

When we look at details we see that prominent “features” in one map of a specific 4-image do NOT appear in a fully comparable way in the eventual convolutional maps for another image of a “4”. Some of the maps (i.e. filters after 4 transformations) produce really different results for our three images.

But there are common elements, too: I have marked only some of the points which show a significant intensity in all of the maps. But does this mean these individual common points are decisive for a classification of a “4”? We cannot be sure about it – probably it is their combination which is relevant.

So, what we ended up with is that we find some common points or some common point-relations in a few of the 128 “3×3”-maps of our three images of handwritten “4”s.

But how does this compare with maps of images of other digits? Well, look at he maps on the 3rd layer for images of a “1” and a “2” respectively:

On the 3rd layer it becomes more important which maps are not activated at all. But still the activation patterns within certain maps seem to be of importance for an eventual classification.


The maps of a CNN are created by an effective and guided optimization process. The results indicate the eventual detection of rather abstract patterns within and across filter maps on higher convolutional layers.

But these patterns (FCP-patterns) should not be confused with figurative elements or “features” in the original input images. Activation patterns at best vaguely remind of the original image features. At our level of analysis of a CNN we can only speculate about some correspondence of map activations with original features or patterns in an input image.

But it seems pretty clear that patterns in or across maps do not indicate any kind of constructive concept which describes how to build a “4” from underlying more elementary features in the sense of combine-able independent entities. There is no sign of conceptual constructive idea of how to denote a “4”. At least not in pure CNNs … Things may be a bit different in convolutional “autoencoders” (combinations of convolutional encoders and decoders), but this is another story we will come back to in this blog. Right now we would say that abstract (FCP-) patterns in maps of higher convolutional layers result from intricate filter combinations. These filters may react to certain patterns in an input image – but whether these patterns correspond to entities a human being would use to write down and thereby construct a “4” or an “8” is questionable.

We saw that the abstract information maps at the third layer of our CNN do show some common elements between the images belonging to the same class – and delicate differences with respect to activations resulting from images of other classes. However, the differences reside in details and the situation remains complicated. In the end the MLP-part of a CNN still has a lot of work to do. It must perform its classification task based on the correlation or anti-correlation of “point”-like elements in a multitude of maps – and probably even based on the activation level (i.e. output numbers) at these points.

This is seemingly very different from a conscious consideration process and weighing of alternatives which a human brain performs when it looks at sketches of numbers. When in doubt our brain tries to find traces consistent with a construction process defined for writing down a “4”, i.e. signs of a certain arrangement of straight and curved lines. A human brain, thus, would refer to arrangements of line elements, bows or circles – but not to relations of individual points in an extremely coarse and abstract representation space after some mathematical transformations. You may now argue that we do not need such a process when looking at clear representations of a “4” – we look and just know that its a “4”. I do not doubt that a brain may use maps, too – but I want to point out that a conscious intelligent thought process and conceptual ideas about entities involve constructive operations and not just a passive application of filters. Even from this extremely simplifying point of view CNNs are stupid though efficient algorithms. And authors writing about “features” should avoid any kind of a humanized interpretation.

In the next article

A simple CNN for the MNIST dataset – VI – classification by activation patterns and the role of the CNN’s MLP part

we shall look at the whole procedure again, but then we compare common elements of a “4” with those of a “9” on the 3rd convolutional layer. Then the key question will be: ” What do “4”s have in common on the last convolutional maps which corresponding activations of “9”s do not show – and vice versa.

This will become especially interesting in cases for which a distinction was difficult for pure MLPs. You remember the confusion matrix for the MNIST dataset? See:
A simple Python program for an ANN to cover the MNIST dataset – XI – confusion matrix
We saw at that point in time that pure MLPs had some difficulties to distinct badly written “4”s from “9s”. We will see that the better distinction abilities of CNNs in the end depend on very few point like elements of the eventual activation on the last layer before the MLP.

Further articles in this series

A simple CNN for the MNIST dataset – VII – outline of steps to visualize image patterns which trigger filter maps
A simple CNN for the MNIST dataset – VI – classification by activation patterns and the role of the CNN’s MLP part


A single neuron perceptron with sigmoid activation function – II – normalization to overcome saturation

I continue my small series on a single neuron perceptron to study the positive effects of the normalization of input data in combination with the use of the sigmoid function as the activation function. In the last article

A single neuron perceptron with sigmoid activation function – I – failure of gradient descent due to saturation

we have seen that the saturation of the sigmoid function for big positive or negative arguments can prevent a smooth gradient descent under certain conditions – even if a global minimum clearly exists.

A perceptron with just one computing neuron is just a primitive example which demonstrates what can happen at the neurons of the first computing layer after the input layer of a real “Artificial Neural Network” [ANN]. We should really avoid to provide too big input values there and take into account that input values for different features get added up.

Measures against saturation at neurons in the first computing layer

There are two elementary methods to avoid saturation of sigmoid like functions at neurons of the first hidden layer:

  • Normalization: One measure to avoid big input values is to normalize the input data. Normalization can be understood as a transformation of given real input values for all of the features into an interval [0, 1] or [-1, 1]. There are of course many transformations which map a real number distribution into a given limited interval. Some keep up the relative distance of data points, some not. We shall have a look at some standard normalization variants used in Machine Learning [ML] during this and the next article .
    The effect with respect to a sigmoidal activation function is that the gradient for arguments in the range [-1, 1] is relatively big. The sigmoid function behaves almost as a linear function in this argument region; see the plot in the last article.
  • Choosing an appropriate (statistical) initial weight distribution: If we have a relatively big feature space as e.g. for the MNIST dataset with 784 features, normalization alone is not enough. The initial value distribution for weights must also be taken care of as we add up contributions of all input nodes (multiplied by the weights). We can follow a recommendation of LeCun (1990); see the book of Aurelien Geron recommended (here) for more details.
    Then we would choose a uniform distribution of values in a range [-alpha*sqrt(1/num_inp_nodes), alpha*sqrt(1/num_inp_nodes)], with alpha $asymp; 1.73 and num_inp_nodes giving the number of input nodes, which typically is the number of features plus 1, if you use a bias neuron. As a rule of thumb I personally take [-0.5*sqrt(1/num_inp_nodes, 0.5*sqrt[1/num_inp_nodes].

Normalization functions

The following quick&dirty Python code for a Jupyter cell calls some normalization functions for our simple perceptron scenario and directly executes the transformation; I have provided the required import statements for libraries already in the last article.

# ********
# Scaling
# ********

b_scale = True
scale_method = 3
# 0: Normalizer (standard), 1: StandardScaler, 2. By factor, 3: Normalizer per pair 
# 4: Min_Max, 5: Identity (no transformation) - just there for convenience  

shape_ay = (num_samples,)
ay_K1 = np.zeros(shape_ay)
ay_K2 = np.zeros(shape_ay)

# apply scaling
if b_scale:
    # shape_input = (num_samples,2)
    rg_idx = range(num_samples)
    if scale_method == 0:
        shape_input = (2, num_samples)
        ay_K = np.zeros(shape_input)
        for idx in rg_idx:
            ay_K[0][idx] = li_K1[idx] 
            ay_K[1][idx] = li_K2[idx] 
        scaler = Normalizer()
        ay_K = scaler.fit_transform(ay_K)
        for idx in rg_idx:
            ay_K1[idx] = ay_K[0][idx]   
            ay_K2[idx] = ay_K[1][idx] 
    elif scale_method == 1: 
        shape_input = (num_samples,2)
        ay_K = np.zeros(shape_input)
        for idx in rg_idx:
            ay_K[idx][0] = li_K1[idx] 
            ay_K[idx][1] = li_K2[idx] 
        scaler = StandardScaler()
        ay_K = scaler.fit_transform(ay_K)
        for idx in rg_idx:
            ay_K1[idx] = ay_K[idx][0]   
            ay_K2[idx] = ay_K[idx][1]
    elif scale_method == 2:
        dmax = max(li_K1.max() - li_K1.min(), li_K2.max() - li_K2.min())
        ay_K1 = 1.0/dmax * li_K1
        ay_K2 = 1.0/dmax * li_K2
    elif scale_method == 3:
        shape_input = (num_samples,2)
        ay_K = np.zeros(shape_input)
        for idx in rg_idx:
            ay_K[idx][0] = li_K1[idx] 
            ay_K[idx][1] = li_K2[idx] 
        scaler = Normalizer()
        ay_K = scaler.fit_transform(ay_K)
        for idx in rg_idx:
            ay_K1[idx] = ay_K[idx][0]   
            ay_K2[idx] = ay_K[idx][1]
    elif scale_method == 4:
        shape_input = (num_samples,2)
        ay_K = np.zeros(shape_input)
        for idx in rg_idx:
            ay_K[idx][0] = li_K1[idx] 
            ay_K[idx][1] = li_K2[idx] 
        scaler = MinMaxScaler()
        ay_K = scaler.fit_transform(ay_K)
        for idx in rg_idx:
            ay_K1[idx] = ay_K[idx][0]   
            ay_K2[idx] = ay_K[idx][1]
    elif scale_method == 5:
        ay_K1 = li_K1
        ay_K2 = li_K2
# Get overview over costs on weight-mesh
wm1 = np.arange(-5.0,5.0,0.002)
wm2 = np.arange(-5.0,5.0,0.002)
#wm1 = np.arange(-0.3,0.3,0.002)
#wm2 = np.arange(-0.3,0.3,0.002)
W1, W2 = np.meshgrid(wm1, wm2) 
C, li_C_sgl = costs_mesh(num_samples = num_samples, W1=W1, W2=W2, li_K1 = ay_K1, li_K2 = ay_K2, \
                               li_a_tgt = li_a_tgt)

C_min = np.amin(C)
print("C_min = ", C_min)
IDX = np.argwhere(C==C_min)
print ("Coordinates: ", IDX)
wmin1 = W1[IDX[0][0]][IDX[0][1]] 
wmin2 = W2[IDX[0][0]][IDX[0][1]]
print("Weight values at cost minimum:",  wmin1, wmin2)

# Plots
# ******
fig_size = plt.rcParams["figure.figsize"]
fig_size[0] = 19; fig_size[1] = 19

fig3 = plt.figure(3); fig4 = plt.figure(4)

ax3 = fig3.gca(projection='3d')
ax3.get_proj = lambda: np.dot(Axes3D.get_proj(ax3), np.diag([1.0, 1.0, 1, 1]))
ax3.set_xlabel('w1', fontsize=16)
ax3.set_ylabel('w2', fontsize=16)
ax3.set_zlabel('Total costs', fontsize=16)
ax3.plot_wireframe(W1, W2, 1.2*C, colors=('green'))

ax4 = fig4.gca(projection='3d')
ax4.get_proj = lambda: np.dot(Axes3D.get_proj(ax4), np.diag([1.0, 1.0, 1, 1]))
ax4.set_xlabel('w1', fontsize=16)
ax4.set_ylabel('w2', fontsize=16)
ax4.set_zlabel('Single costs', fontsize=16)
ax4.plot_wireframe(W1, W2, li_C_sgl[0], colors=('blue'))
#ax4.plot_wireframe(W1, W2, li_C_sgl[1], colors=('red'))
ax4.plot_wireframe(W1, W2, li_C_sgl[5], colors=('orange'))
#ax4.plot_wireframe(W1, W2, li_C_sgl[6], colors=('yellow'))
#ax4.plot_wireframe(W1, W2, li_C_sgl[9], colors=('magenta'))
#ax4.plot_wireframe(W1, W2, li_C_sgl[12], colors=('green'))



The results of the transformation for our two features are available in the arrays “ay_K1” and “ay_K2”. These arrays will then be used as an input to gradient descent.

remarks on some normalization methods:

Normalizer: It is in the above code called by setting “scale_method=0”. The “Normalizer” with standard parameters scales by applying a division by an averaged L2-norm distance. However, its application is different from other SciKit-Learn scalers:
It normalizes over all data given in a sample. The dimensions beyond 1 are NOT interpreted as features which have to be normalizes separately – as e.g. the “StandardScaler” does. So, you have to be careful with index handling! This explains the different index-operation for “scale_method = 0” compared to other cases.

StandardScaler: Called by setting “scale_method=1”. The StandardScaler accepts arrays of samples with columns for features. It scales all features separately. It subtracts the mean average of all feature values of all samples and divides afterwards by the standard deviation. It thus centers the value distribution with a mean value of zero and a variance of 1. Note however that it does not limit all transformed values to the interval [-1, 1].

MinMaxScaler: Called by setting “scale_method=4”. The MinMaxScaler
works similar to the StandardScaler but subtracts the minimum and divides by the (max-min)-difference. It therefore does not center the distribution and does not set the variance to 1. However, it limits the transformed values to the interval [-1, 1].

Normalizer per sample: Called by setting “scale_method=3”. This applies the Normalizer per sample! I.e., it scales in our case both the given feature values for one single by their mean and standard deviation. This may at first sound totally meaningless. But we shall see in the next article that it is not in case for our special set of 14 input samples.

Hint: For the rest of this article we shall only work with the StandardScaler.

Input data transformed by the StandardScaler

The following plot shows the input clusters after a transformation with the “StandardScaler”:

You should recognize two things: The centralization of the features and the structural consistence of the clusters to the original distribution before scaling!

The cost hyperplane over the {w1, w2}-space after the application of the StandardScaler to our input data

Let us apply the StandardScaler and look at the resulting cost hyperplane. When we set the parameters for a mesh display to

wm1 = np.arange(-5.0,5.0,0.002), wm2 = np.arange(-5.0,5.0,0.002)

we get the following results:

C_min =  0.0006239618496774544
Coordinates:  [[2695 2259]]
Weight values at cost minimum: -0.4820000000004976 0.3899999999994064

Plots for total costs over the {w1, w2}-space from different angles

Plot for individual costs (i=0, i=5) over the {w1, w2}-space

The index “i” refers to our sample-array (see the last article).

Gradient descent after scaling with the “StandardScaler”

Ok, let us now try gradient descent again. We set the following parameters:

w1_start = -0.20, w2_start = 0.25 eta = 0.1, decrease_rate = 0.000001, num_steps = 2000


Stoachastic Descent
          Kt1       Kt2     K1     K2  Tgt       Res       Err
0   1.276259 -0.924692  200.0   14.0  0.3  0.273761  0.087463
1  -1.067616  0.160925    1.0  107.0  0.7  0.640346  0.085220
2   0.805129 -0.971385  160.0   10.0  0.3  0.317122  0.057074
3  -0.949833  1.164828   11.0  193.0  0.7  0.713461  0.019230
4   1.511825 -0.714572  220.0   32.0  0.3  0.267573  0.108090
5  -0.949833  0.989729   11.0  178.0  0.7  0.699278  0.001031
6   0.333998 -1.064771  120.0    2.0  0.3  0.359699  0.198995
7  -0.914498  1.363274   14.0  210.0  0.7  0.725667  0.036666
8   1.217368 -0.948038  195.0   12.0  0.3  0.277602  0.074660
9  -0.902720  0.476104   15.0  134.0  0.7  0.650349  0.070930
10  0.451781 -1.006405  130.0    7.0  0.3  0.351926  0.173086
11 -1.020503  0.861322    5.0  167.0  0.7  0.695876  0.005891
12  1.099585 -0.971385  185.0   10.0  0.3  0.287246  0.042514
13 -0.890942  1.585067   16.0  229.0  0.7  0.740396  0.057709

Batch Descent
          Kt1       Kt2     K1     K2  Tgt       Res       Err
0   1.276259 -0.924692  200.0   14.0  0.3  0.273755  0.087482
1  -1.067616  0.160925    1.0  107.0  0.7  0.640352  0.085212
2   0.805129 -0.971385  160.0   10.0  0.3  0.317118  0.057061
3  -0.949833  1.164828   11.0  193.0  0.7  0.713465  0.019236
4   1.511825 -0.714572  220.0   32.0  0.3  0.267566  0.108113
5  -0.949833  0.989729   11.0  178.0  0.7  0.699283  0.001025
6   0.333998 -1.064771  120.0    2.0  0.3  0.359697  0.198990
7  -0.914498  1.363274   14.0  210.0  0.7  0.725670  0.036672
8   1.217368 -0.948038  195.0   12.0  0.3  0.277597  0.074678
9  -0.902720  0.476104   15.0  134.0  0.7  0.650354  0.070923
10  0.451781 -1.006405  130.0    7.0  0.3  0.351924  0.173080
11 -1.020503  0.861322    5.0  167.0  0.7  0.695881  0.005884
12  1.099585 -0.971385  185.0   10.0  0.3  0.287241  0.042531
13 -0.890942  1.585067   16.0  229.0  0.7  0.740400  0.057714

Total error stoch descent:  0.07275422919538276
Total error batch descent:  0.07275715820661666

The attentive reader has noticed that I extended my code to include the columns with the original (K1, K2)-values into the Pandas dataframe. The code of the new function “predict_batch()” is given below. Do not forget to change the function calls at the end of the gradient descent code, too.

Now we obviously can speak of a result! The calculated (w1, w2)-data are:

Final (w1,w2)-values stoch : ( -0.4816 ,  0.3908 )
Final (w1,w2)-values batch : ( -0.4815 ,  0.3906 )

Yeah, this is pretty close to the values we got via the fine grained mesh analysis of the cost function before! And within the error range!

Changed code for two of our functions in the last article

def predict_batch(num_samples, w1, w2, ay_k_1, ay_k_2, li_K1, li_K2, li_a_tgt):
    shape_res = (num_samples, 7)
    ResData = np.zeros(shape_
    rg_idx = range(num_samples)
    err = 0.0
    for idx in rg_idx:
        z_in  = w1 * ay_k_1[idx] + w2 * ay_k_2[idx] 
        a_out = expit(z_in)
        a_tgt = li_a_tgt[idx]
        err_idx = np.absolute(a_out - a_tgt) / a_tgt 
        err += err_idx
        ResData[idx][0] = ay_k_1[idx] 
        ResData[idx][1] = ay_k_2[idx] 
        ResData[idx][2] = li_K1[idx] 
        ResData[idx][3] = li_K2[idx] 
        ResData[idx][4] = a_tgt
        ResData[idx][5] = a_out
        ResData[idx][6] = err_idx
    err /= float(num_samples)
    return err, ResData    

def create_df(ResData):
    ''' ResData: Array with result values K1, K2, Tgt, A, rel.err 
    cols=["Kt1", "Kt2", "K1", "K2", "Tgt", "Res", "Err"]
    df = pd.DataFrame(ResData, columns=cols)
    return df    


How does the epoch evolution after the application of the StandardScaler look like?

Let us plot the evolution for the stochastic gradient descent:

Cost and weight evolution during stochastic gradient descent

Ok, we see that despite convergence the difference in the costs for different samples cannot be eliminated. It should be clear to the reader, why, and that this was to be expected.

We also see that the total costs (calculated from the individual costs) seemingly converges much faster than the weight values! Our gradient descent path obviously follows a big slope into a rather flat valley first (see the plot of the total costs above). Afterwards there is a small gradient sideways and down into the real minimum – and it obviously takes some epochs to get there. We also understand that we have to keep up a significant “learning rate” to follow the gradient in the flat valley. In addition the following rule seems to be appropriate sometimes:

We must not only watch the cost evolution but also the weight evolution – to avoid stopping gradient descent too early!

We shall keep this in mind for experiments with real multi-layer “Artificial Neural Networks” later on!

And how does the gradient descent based on the full “batch” of 14 samples look like?

Cost and weight evolution during batch gradient descent

A smooth beauty!

Contour plot for separation curves in the {K1, K2}-plane

We add the following code to our Jupyter notebook:

# ***********
# Contours 
# ***********

from matplotlib import ticker, cm

# Take w1/w2-vals from above w1f, w2f
w1_len = len(li_w1_ba)
w2_len = len(li_w1_ba)
w1f = li_w1_ba[w1_len -1]
w2f = li_w2_ba[w2_len -1]

def A_mesh(w1,w2, Km1, Km2):
    kshape = Km1.shape
    A = np.zeros(kshape) 
    Km1V = Km1.reshape(kshape[0]*kshape[1], )
    Km2V = Km2.reshape(kshape[0]*kshape[1], )
    # print("km1V.shape = ", Km1V.shape, "\nkm1V.shape = ", Km2V.shape )
    KmV = np.column_stack((Km1V, Km2V))
    # scaling trafo
    KmT = scaler.transform(KmV)
    Km1T, Km2T = KmT.T
    Km1TR = Km1T.reshape(
    Km2TR = Km2T.reshape(kshape)
    #print("km1TR.shape = ", Km1TR.shape, "\nkm2TR.shape = ", Km2TR.shape )
    rg_idx = range(num_samples)
    Z      = w1 * Km1TR + w2 * Km2TR
    A = expit(Z)
    return A

#Build K1/K2-mesh 
minK1, maxK1 = li_K1.min()-20, li_K1.max()+20 
minK2, maxK2 = li_K2.min()-20, li_K2.max()+20
resolution = 0.1
Km1, Km2 = np.meshgrid( np.arange(minK1, maxK1, resolution), 
                        np.arange(minK2, maxK2, resolution))

A = A_mesh(w1f, w2f, Km1, Km2 )

fig_size = plt.rcParams["figure.figsize"]
fig_size[0] = 14
fig_size[1] = 11
fig, ax = plt.subplots()
#cs = plt.contourf(X, Y, Z1, levels=25, alpha=1.0, cmap=cm.PuBu_r)
cs = ax.contourf(Km1, Km2, A, levels=25, alpha=1.0, cmap=cmap)
cbar = fig.colorbar(cs)
N = 14
r0 = 0.6
x = li_K1
y = li_K2
area = 6*np.sqrt(x ** 2 + y ** 2)  # 0 to 10 point radii
c = np.sqrt(area)
r = np.sqrt(x ** 2 + y ** 2)
area1 = np.ma.masked_where(x < 100, area)
area2 = np.ma.masked_where(x >= 100, area)
ax.scatter(x, y, s=area1, marker='^', c=c)
ax.scatter(x, y, s=area2, marker='o', c=c)
# Show the boundary between the regions:
ax.set_xlabel("K1", fontsize=16)
ax.set_ylabel("K2", fontsize=16)


This code enables us to plot contours of predicted output values of our solitary neuron, i.e. A-values, on a mesh of the original {K1, K2}-plane. As we classified after a transformation of our input data, the following hint should be obvious:

Important hint: Of course you have to apply your scaling method to all the new input data created by the mesh-function! This is done in the above code in the “A_mesh()”-function with the following lines:

    # scaling trafo
    if (scale_method == 3): 
        KmT = scaler.fit_transform(KmV)
        KmT = scaler.transform(KmV)

We can directly apply the StandardScaler on our new data via its method transform(); the scaler will use the parameters it found during his first “scaler.fit_transform()”-operation on our input samples. However, we cannot do it this way when using the Normalizer for each individual new data sample via “scale_method =3”. I shall come back to this point in a later article.

The careful reader also sees that our code will, for the time being, not work for scale_method=0, scale_method=2 and scale_method=5. Reason: I was too lazy to write a class or code suitable for these normalizing operations. I shall correct this when we need it.

But at least I added our input samples via scatter plotting to the final output. The result is:

The deviations from our target values is to be expected. With a given pair of (w1, w2)-values we cannot do much better with a single neuron and a linear weight impact on the input data.

But we see: If we set up a criterion like:

  • A > 0.5 => sample belongs to the left cluster,
  • A ≤ 0.5 => sample belongs to the right cluster

we would have a relatively good classificator available – based on one neuron only!

Intermediate Conclusion

In this article I have shown that the “standardization” of input data, which are fed into a perceptron ahead of a gradient descent calculation, helps to circumvent problems with the saturation of the sigmoid function at the computing neuron following the input layer. We achieved this by applying the ”
StandardScaler” of Scikit-Learn. We got a smooth development of both the cost function and the weight parameters during gradient descent in the transformed data space.

We also learned another important thing:

An apparent convergence of the cost function in the vicinity of a minimum value does not always mean that we have reached the global minimum, yet. The evolution of the weight parameters may not yet have come to an end! Therefore, it is important to watch both the evolution of the costs AND the evolution of the weights during gradient descent. A too fast decline of the learning rate may not be good either under certain conditions.

In the next article

A single neuron perceptron with sigmoid activation function – III – two ways of applying Normalizer

we shall look at two other normalization methods for our simplistic scenario. One of them will give us an even better classificator.

Stay tuned and remain healthy …

And Mr Trump:
One neuron can obviously learn something about the difference of big and small numbers. This leads me to two questions, which you as a “natural talent” on epidemics can certainly answer: How many neurons are necessary to understand something about an exponential epidemic development? And why did it take so much time to activate them?