Abstract
Recent advances in the area of deep neural networks brought a lot of attention to some of the key issues important for their design. In particular for 2D-shapes, their accuracy has been shown to outperform all other classifiers.
On the other hand, their training may be quite cumbersome and the structure of the network has to be chosen beforehand. This paper introduces a new sensitivity-based approach capable of picking the right image features from a pre-trained SOM-like feature detector.
Experimental results obtained so far for hand-written digit recognition show that pruned network architectures impact a transparent representation of the features actually present in the data while improving network robustness. The technical report represents an extended version of our article entitled "Can Deep Neural Networks Discover Meaningful Pattern Features?"