Get the latest tech news
TopoNets: High-Performing Vision and Language Models with Brain-Like Topography
ICLR 2025 The organization of neurons in the brain is highly structured: neurons performing similar functions are located near one another. This "topographic organization" is a fundamental principle of primate brains and plays an important role in shaping the brain's representations.
Here we introduce TopoLoss, a simple, scalable, and effective method for inducing brain-like topography into leading AI architectures (convolutional networks and transformers) with minimal drop in model performance. Studies using fMRI and invasive recordings (for example: Regev et al.) have provided evidence for distinct temporal receptive fields. We would like to thank Anna Ivanova, Alish Dipani, Taha Binhuraib and everyone at Murty lab for their valuable feedback and support.
Or read this on Hacker News
