psycho_ai's Introduction

`psycho_ai`: analyzing biases in AI models using Psychophysics

Authors

Lizhen Liang, Ph.D. student, Syracuse University
Daniel E. Acuna, iSchool, Syracuse University

Introduction

Install:

pip install git+https://github.com/sciosci/psycho_ai

Examples

Extract PSE and JND of word embedding models:

from psycho_ai import two_afc

embedding = two_afc.get_glove_100d()
target_occupations = ['accountant', 'supervisor', 'worker', 'clerk', 'instructor', 'inspector',
          'electrician','appraiser', 'administrator', 'receptionist', 'advisor', 'chemist',
          'planner','paralegal', 'veterinarian', 'psychologist',  'baker', 'teacher', 
          'lawyer','nutritionist', 'hairdresser','pathologist', 'surgeon', 'practitioner', 
          'carpenter']
female_male_pairs = [['woman', 'man'],
                     ['female', 'male'],
                     ['she', 'he'],
                     ['her', 'him'],
                     ['hers', 'his'],
                     ['daughter', 'son'],
                     ['girl', 'boy'],
                     ['sister', 'brother']]
                
pse_score = two_afc.pse(embedding, target_occupations, female_male_pairs)
jnd_score = two_afc.jnd([embedding_A,embedding_B],target_occupations, female_male_pairs)

PSE Score

{'advisor': 0.23486328125,
 'architect': 0.24462890625,
 'officer': 0.29150390625,
 ...
 ...
 ...
 'therapist': 0.7587890625,
 'hairdresser': 0.76513671875,
 'hygienist': 0.830078125}

JND Score

{'janitor': 0.0010945320129394534,
'technician': 0.0012115716934204103,
'administrator': 0.0013679265975952148,
...
...
...
'supervisor': 0.021092605590820313,
'architect': 0.022199630737304688,
'plumber': 0.02711360454559326}

Plots

two_afc.plot_pse(pse_score)

Citation

Please refer to

Liang, L., & Acuna, D. E. (2020, January) . Artificial mental phenomena: Psychophysics as a framework to detect perception biases in AI models . In Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency ( pp. 403-412).

psycho_ai's People

Contributors

Stargazers

Watchers

psycho_ai's Issues

Create API for supervised learning task

We need an API to estimate the PSE and JNE of a given attribute for a supervised learning task. This API should interact with sklearn.

from sklearn.linear_model import LogisticRegression

# classification problem: whether to approve a loan or not. Features in X and binary outcomes in y
model = LogisticRegression()
model.fit(X, y)

# import package to examine the model
from psycho_ai import two_afc

# let's assume that attribute 5 is "gender" and "training_X" is the data used for training.
pse = two_afc.pse(model, attribute=5, training_X = X)
# pse will contain the point of subjective equivalence for attribute 5.

Run 2AFC for extracting JND for arbitrary word embedding tasks according to paper

The code should look something like

from psycho_ai import two_afc
# "embeddings" should be a list of word embedding dictionaries
jnd = two_afc.pse(target_words, left_words, right_words, embeddings)

Run 2AFC for extracting PSE for arbitrary word embedding tasks according to paper

The code should look something like

from psycho_ai import two_afc
pse = two_afc.pse(target_words, left_words, right_words, embedding)

Recommend Projects

React

A declarative, efficient, and flexible JavaScript library for building user interfaces.

Vue.js

🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

Typescript

TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

TensorFlow

An Open Source Machine Learning Framework for Everyone

Django

The Web framework for perfectionists with deadlines.

Laravel

A PHP framework for web artisans

D3

Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

javascript

JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

web

Some thing interesting about web. New door for the world.

server

A server is a program made to process requests and deliver data to clients.

Machine learning

Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

Visualization

Some thing interesting about visualization, use data art

Game

Some thing interesting about game, make everyone happy.

Recommend Org

Facebook

We are working to build community through open source technology. NB: members must have two-factor auth.

Microsoft

Open source projects and samples from Microsoft.

Google

Google ❤️ Open Source for everyone.

Alibaba

Alibaba Open Source for everyone

D3

Data-Driven Documents codes.

Tencent

China tencent open source team.

sciosci / psycho_ai Goto Github PK