Skip to content

Research Talk 4

Title: Functional Connectomes of Neural Networks

Speaker: Yutong Wu

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. This talk presents a novel approach that bridges neural networks and human brain functions by leveraging brain-inspired techniques. Grounded in insights from the functional connectome, this approach offers scalable ways to characterize the topology of large neural networks using stable statistical and machine learning techniques. Empirical analysis demonstrates its potential to enhance interpretability, providing a deeper understanding of underlying mechanisms.

The full peer-reviewed paper is available at https://arxiv.org/pdf/2412.15279.