SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1605.01713 · 2016

Not Just a Black Box: Learning Important Features Through Propagating Activation Differences

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

Note: This paper describes an older version of DeepLIFT. See https://arxiv.org/abs/1704.02685 for the newer version. Original abstract follows: The purported "black box" nature of neural networks is a barrier to adoption in applications where interpretability is essential. Here we present DeepLIFT (Learning Important FeaTures), an efficient and effective method for computing importance scores in a neural network. DeepLIFT compares the activation of each neuron to its 'reference activation' and assigns contribution scores according to the difference. We apply DeepLIFT to models trained on natural images and genomic data, and show significant advantages over gradient-based methods.

For agents

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

get_harvested_code_for_paper("1605.01713")
get_code_for_paper("1605.01713")
have("1605.01713")

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

curl https://syntology.ai/api/ran/1605.01713.json

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

[![Syntology run record](https://syntology.ai/api/ran/1605.01713.svg)](https://syntology.ai/paper/1605.01713)

Connect an agent — have() is free.