Functional connectomes of neural networks

TL;DR

This paper introduces a brain-inspired method to analyze neural networks by leveraging functional connectome techniques, improving interpretability and understanding of neural network mechanisms.

Contribution

It presents a novel approach that applies functional connectome analysis to neural networks, bridging neuroscience and machine learning for better interpretability.

Findings

Enhanced interpretability of neural networks

Scalable characterization of network topology

Deeper understanding of neural mechanisms

Abstract

The human brain is a complex system, and understanding its mechanisms has been a long-standing challenge in neuroscience. The study of the functional connectome, which maps the functional connections between different brain regions, has provided valuable insights through various advanced analysis techniques developed over the years. Similarly, neural networks, inspired by the brain's architecture, have achieved notable success in diverse applications but are often noted for their lack of interpretability. In this paper, we propose a novel approach that bridges neural networks and human brain functions by leveraging brain-inspired techniques. Our approach, grounded in the insights from the functional connectome, offers scalable ways to characterize topology of large neural networks using stable statistical and machine learning techniques. Our empirical analysis demonstrates its capability to enhance the interpretability of neural networks, providing a deeper understanding of their underlying mechanisms.