Enhanced Deep Learning with Improved Feature Subspace Separation

Date

2018-09-30

Author

Parlaktuna, Mustafa
Sekmen, Ali
Koku, Ahmet Buğra
Abdul Malek, Ayad

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

14
views

0
downloads

Cite This

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.

Subject Keywords

Deep convolutional networks, Deep learning, Subspace separation

URI

https://hdl.handle.net/11511/55116

Collections

Department of Mechanical Engineering, Conference / Seminar