Guiding Sparse Neural Networks with Neurobiological Principles to Elicit Biologically Plausible Representations

TL;DR

This paper introduces a biologically inspired learning rule for neural networks that incorporates neurobiological principles like sparsity and Dale's law, improving robustness, generalization, and the emergence of plausible neural representations.

Contribution

It presents a novel neurobiologically inspired learning rule that naturally enforces key biological principles without explicit constraints, enhancing neural network performance and interpretability.

Findings

Improved robustness against adversarial attacks

Enhanced generalization in few-shot learning

Emergence of biologically plausible neural representations

Abstract

While deep neural networks (DNNs) have achieved remarkable performance in tasks such as image recognition, they often struggle with generalization, learning from few examples, and continuous adaptation - abilities inherent in biological neural systems. These challenges arise due to DNNs' failure to emulate the efficient, adaptive learning mechanisms of biological networks. To address these issues, we explore the integration of neurobiologically inspired assumptions in neural network learning. This study introduces a biologically inspired learning rule that naturally integrates neurobiological principles, including sparsity, lognormal weight distributions, and adherence to Dale's law, without requiring explicit enforcement. By aligning with these core neurobiological principles, our model enhances robustness against adversarial attacks and demonstrates superior generalization, particularly in few-shot learning scenarios. Notably, integrating these constraints leads to the emergence of biologically plausible neural representations, underscoring the efficacy of incorporating neurobiological assumptions into neural network design. Preliminary results suggest that this approach could extend from feature-specific to task-specific encoding, potentially offering insights into neural resource allocation for complex tasks.