attributionpriors

Tools for training explainable models using attribution priors.

Intended Audience
- Science/Research
License
- OSI Approved :: MIT License
Operating System
- OS Independent
Programming Language
- Python :: 3
Topic
- Scientific/Engineering

Project description

This package contains tools to train deep learning models using attribution priors. Through attribution priors, practitioners can constraint models to behave more intuitively on a wide variety of tasks. For usage guidelines, see the GitHub repo. For more details about how to use attribution priors, see the arXiv paper.

Project details

Intended Audience
- Science/Research
License
- OSI Approved :: MIT License
Operating System
- OS Independent
Programming Language
- Python :: 3
Topic
- Scientific/Engineering

Release history Release notifications | RSS feed

This version

0.1.3

Oct 31, 2019

0.1.2

Jul 18, 2019

0.1.1

Jun 27, 2019

0.1

Jun 25, 2019

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

attributionpriors-0.1.3.tar.gz (15.1 kB view hashes)

Uploaded Oct 31, 2019 Source

Built Distribution

attributionpriors-0.1.3-py3-none-any.whl (15.5 kB view hashes)

Uploaded Oct 31, 2019 Python 3

Hashes for attributionpriors-0.1.3.tar.gz

Hashes for attributionpriors-0.1.3.tar.gz
Algorithm	Hash digest
SHA256	`21302fae6208ffdbf43374e4dcb59ef7c3825d47e9b8e8a53a8366d1906502b4`
MD5	`03491a58bddca0bec7f379fcdf2067e2`
BLAKE2b-256	`a8493765b51b830d177a26fc1e7b26e56bce9a1421ee532f14dbbdf25764ea45`

Hashes for attributionpriors-0.1.3-py3-none-any.whl

Hashes for attributionpriors-0.1.3-py3-none-any.whl
Algorithm	Hash digest
SHA256	`2a64faee9585215a885129e9787e65ca5b04eabbf57344386f2b2811d08bf5e9`
MD5	`c3058b2acdd66c1396e22befaccf5a37`
BLAKE2b-256	`d9809cb508e67459e3c54ed813488fa1ee220e899753b4a02fb9f7036455c39a`