Do traditional algorithms perform better than CNN?

[Christian_Simonis]

Hi @vasyl.delta

I guess you are referring to this:

@Christian_Simonis

DL models basically take care of „feature engineering“

Features learned by DL often lack interpretability and explainability and often do not have a physical meaning or a direct domain meaning, e.g. also embeddings in some hidden layers.

As a theoretic example for DL:

… the model could learn how edges and contours make a „paw“ or „whiskers“ or other features that are important to identify a cat and low level features like edges are hierarchically combined and enhanced to describe more advanced patterns to finally form objects, which contribute to the classification if we see a cat on the picture or not.

see also this thread: New 1000 images after model development (train/dev/test), where to add? - #11 by Christian_Simonis

In reality, things are not always so good to interpret when it comes to DL and in general the explainability of hand crafted features with physical meaning is usually clearly higher.

Also, this thread might be relevant for you:

What makes different neurons calculate different parameters within a layer?

You could also apply a heatmap approach to interpret in a visual way and see in which areas the layer were activated and contributed to the output, see also: Get Heatmap from CNN ( Convolution Neural Network ), AKA CAM | by Seachaos | tree.rocks Also: In figure 1) you find a nice illustrative visualization how low level features like edges are hierarchically combined and enhanced to describe more advanced patterns to finally form objects: see the following Source. see this Thread. Hope that …

Best regards
Christian