SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1610.01644 · 2016

Understanding intermediate layers using linear classifier probes

Yoshua Bengio, Guillaume Alain

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

Neural network models have a reputation for being black boxes. We propose to monitor the features at every layer of a model and measure how suitable they are for classification. We use linear classifiers, which we refer to as "probes", trained entirely independently of the model itself. This helps us better understand the roles and dynamics of the intermediate layers. We demonstrate how this can be used to develop a better intuition about models and to diagnose potential problems. We apply this technique to the popular models Inception v3 and Resnet-50. Among other things, we observe experimentally that the linear separability of features increase monotonically along the depth of the model.

For agents

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

get_harvested_code_for_paper("1610.01644")
get_code_for_paper("1610.01644")
have("1610.01644")

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

curl https://syntology.ai/api/ran/1610.01644.json

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

[![Syntology run record](https://syntology.ai/api/ran/1610.01644.svg)](https://syntology.ai/paper/1610.01644)

Connect an agent — have() is free.