Enhanced Deep Learning with Improved Feature Subspace Separation

Parlaktuna, Mustafa
Sekmen, Ali
Koku, Ahmet Buğra
Abdul Malek, Ayad
This research proposes a new deep convolutional network architecture that improves the feature subspace separation. In training, the system considers M classes of input sets {C-i}(i=1)(M) and M deep convolutional networks {DNi}(i=1)(M) whose filter and other parameters are randomly initialized. For each input class C-i, Convolutional Neural Network generates a set of features F-i. Then, a local subspace S-i is matched for each set F-i. This is followed with a full training of the deep convolutional network DNi based on a decision criteria developed with computation of rejections of all features in {F-i}(i=1)(M) to S-i. Five different deep convolutional network topologies are used to show that the proposed technique works better for small network topologies and has comparable performance to more complex networks.