Synthesizing Deep Neural Network Architectures using Biological Synaptic Strength Distributions
Neural and Evolutionary Computing
2017-07-04 v1 Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
Abstract
In this work, we perform an exploratory study on synthesizing deep neural networks using biological synaptic strength distributions, and the potential influence of different distributions on modelling performance particularly for the scenario associated with small data sets. Surprisingly, a CNN with convolutional layer synaptic strengths drawn from biologically-inspired distributions such as log-normal or correlated center-surround distributions performed relatively well suggesting a possibility for designing deep neural network architectures that do not require many data samples to learn, and can sidestep current training procedures while maintaining or boosting modelling performance.
Cite
@article{arxiv.1707.00081,
title = {Synthesizing Deep Neural Network Architectures using Biological Synaptic Strength Distributions},
author = {A. H. Karimi and M. J. Shafiee and A. Ghodsi and A. Wong},
journal= {arXiv preprint arXiv:1707.00081},
year = {2017}
}