Synthesizing Deep Neural Network Architectures using Biological Synaptic Strength Distributions

TL;DR

This paper explores the use of biological synaptic strength distributions to synthesize deep neural networks, showing that biologically-inspired initializations can improve performance especially with small datasets, potentially reducing training requirements.

Contribution

It introduces a novel approach of using biological synaptic distributions for neural network synthesis, highlighting their effectiveness in low-data scenarios.

Findings

Biologically-inspired distributions like log-normal improve performance.

Networks with these distributions perform well with limited data.

Potential to reduce training complexity by using biologically-based initializations.

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.