SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1806.08716 · 2018

Learning Qualitatively Diverse and Interpretable Rules for Classification

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 5 functions out of this paper's own repositories and ran 5 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
dtak/local-independence-public canonical 5 of 5
FunctionStatusWhere it lives
conv_initializer Ran dtak/local-independence-public/beta_vae.py
code served (permissive licence) · get_code("0589d333d30064fb")
fc_initializer Ran dtak/local-independence-public/beta_vae.py
code served (permissive licence) · get_code("23a8fceb6d37f5dd")
l1_loss Ran dtak/local-independence-public/neural_network.py
code served (permissive licence) · get_code("071547946910b3c5")
l2_loss Ran dtak/local-independence-public/neural_network.py
code served (permissive licence) · get_code("3a69a8465f2f99e5")
squared_cos_sim Ran dtak/local-independence-public/neural_network.py
code served (permissive licence) · get_code("731cee44a8b1fc4c")

Repositories linked to this paper

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

Abstract

There has been growing interest in developing accurate models that can also be explained to humans. Unfortunately, if there exist multiple distinct but accurate models for some dataset, current machine learning methods are unlikely to find them: standard techniques will likely recover a complex model that combines them. In this work, we introduce a way to identify a maximal set of distinct but accurate models for a dataset. We demonstrate empirically that, in situations where the data supports multiple accurate classifiers, we tend to recover simpler, more interpretable classifiers rather than more complex ones.

For agents

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

get_harvested_code_for_paper("1806.08716")
get_code_for_paper("1806.08716")
have("1806.08716")

Connect an agent — have() is free.