SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2212.00771 · 2022

Neural Representations Reveal Distinct Modes of Class Fitting in Residual Convolutional Networks

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

We leverage probabilistic models of neural representations to investigate how residual networks fit classes. To this end, we estimate class-conditional density models for representations learned by deep ResNets. We then use these models to characterize distributions of representations across learned classes. Surprisingly, we find that classes in the investigated models are not fitted in an uniform way. On the contrary: we uncover two groups of classes that are fitted with markedly different distributions of representations. These distinct modes of class-fitting are evident only in the deeper layers of the investigated models, indicating that they are not related to low-level image features. We show that the uncovered structure in neural representations correlate with memorization of training examples and adversarial robustness. Finally, we compare class-conditional distributions of neural representations between memorized and typical examples. This allows us to uncover where in the network structure class labels arise for memorized and standard inputs.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2212.00771")
get_code_for_paper("2212.00771")
have("2212.00771")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2212.00771.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2212.00771.svg)](https://syntology.ai/paper/2212.00771)

Connect an agent — have() is free.