Learning Efficient Deep Feature Representations via Transgenerational Genetic Transmission of Environmental Information During Evolutionary Synthesis of Deep Neural Networks

Mohammad J. Shafiee, Elnaz Barshan, Francis Li, Brendan Chwyl, Michelle Karg, Christian Scharfenberger, Alexander Wong; Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2017, pp. 979-986

Abstract


The computational complexity of deep neural networks for extracting deep features is a significant barrier to widespread adoption, particularly for use in embedded devices. One strategy to addressing the complexity issue is the evolutionary deep intelligence framework, which has been demonstrated to enable the synthesis of highly efficient deep neural networks that retain modeling performance. Here, we introduce the notion of trans-generational genetic transmission into the evolutionary deep intelligence framework, where the intra-generational environmental traumatic stresses are imposed to synapses during training to favor the synthesis of more efficient deep neural networks over successive generations. Results demonstrate the efficacy of the proposed framework for synthesizing networks with significant decreases in synapses (e.g., for SVHN, a 230-fold increase in architectural efficiency) while maintaining modeling accuracy and a significantly more efficient feature representation.

Related Material


[pdf]
[bibtex]
@InProceedings{Shafiee_2017_ICCV,
author = {Shafiee, Mohammad J. and Barshan, Elnaz and Li, Francis and Chwyl, Brendan and Karg, Michelle and Scharfenberger, Christian and Wong, Alexander},
title = {Learning Efficient Deep Feature Representations via Transgenerational Genetic Transmission of Environmental Information During Evolutionary Synthesis of Deep Neural Networks },
booktitle = {Proceedings of the IEEE International Conference on Computer Vision (ICCV) Workshops},
month = {Oct},
year = {2017}
}