Papers
arxiv:2312.01280

Brain Decodes Deep Nets

Published on Dec 3, 2023
Authors:
,

Abstract

FactorTopy maps deep network features onto brain fMRI data, revealing insights into training methods and fine-tuning effects on hierarchical organization and scaling behavior.

AI-generated summary

We developed a tool for visualizing and analyzing large pre-trained vision models by mapping them onto the brain, thus exposing their hidden inside. Our innovation arises from a surprising usage of brain encoding: predicting brain fMRI measurements in response to images. We report two findings. First, explicit mapping between the brain and deep-network features across dimensions of space, layers, scales, and channels is crucial. This mapping method, FactorTopy, is plug-and-play for any deep-network; with it, one can paint a picture of the network onto the brain (literally!). Second, our visualization shows how different training methods matter: they lead to remarkable differences in hierarchical organization and scaling behavior, growing with more data or network capacity. It also provides insight into fine-tuning: how pre-trained models change when adapting to small datasets. We found brain-like hierarchically organized network suffer less from catastrophic forgetting after fine-tuned.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2312.01280 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2312.01280 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2312.01280 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.