Efficient Deep Feature Learning and Extraction via StochasticNets

Mohammad Javad Shafiee, Parthipan Siva, Paul Fieguth, Alexander Wong; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2016, pp. 28-36

Abstract


Deep neural networks are a powerful tool for feature learning and extraction. One area worth exploring in feature extraction using deep neural networks is efficient neural connectivity formation for faster feature learning and extraction. Motivated by findings of stochastic synaptic connectivity formation in the brain as well as the brain's uncanny ability to efficiently represent information, we propose the efficient learning and extraction of features via StochasticNets, where sparsely-connected deep neural networks can be formed via stochastic connectivity between neurons. Experimental results show that features learned using deep convolutional StochasticNets, with fewer neural connections than conventional deep convolutional neural networks, can allow for better or comparable classification accuracy than conventional deep neural networks. Finally, it was also shown that significant gains in feature extraction speed can be achieved in embedded applications using StochasticNets.

Related Material


[pdf]
[bibtex]
@InProceedings{Shafiee_2016_CVPR_Workshops,
author = {Javad Shafiee, Mohammad and Siva, Parthipan and Fieguth, Paul and Wong, Alexander},
title = {Efficient Deep Feature Learning and Extraction via StochasticNets},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {June},
year = {2016}
}