A collection of inspiring resources related to engineering management and tech leadership

XAI - An eXplainability toolbox for machine learning

Awesome list about all kinds of interesting topics: Laws, Principles, Mental Models, Cognitive Biases

Bias and Fairness Audit Toolkit

Collaborative text editor (like Google Docs or CoderPad) with integrated semi-anonymizing voice chat intended to help reduce bias in technical communication.

Code for WWW'19 "Unbiased LambdaMART: An Unbiased Pairwise Learning-to-Rank Algorithm", which is based on LightGBM

Explain & debug blackbox machine learning algorithms.

Bias detection in the news. Back and front end for areyoufakenews.com

A curated list of awesome Fairness in AI resources

Automatic synthesis of RCTs

Bluetooth Impersonation AttackS (BIAS) [CVE 2020-10135]

I will update this repository to learn Machine learning with python with statistics content and materials

RUBi : Reducing Unimodal Biases for Visual Question Answering

List of references about Machine Learning and Data Science bias and ethics

Toolkit for Auditing and Mitigating Bias and Fairness of Machine Learning Systems 🔎🤖🧰

Symmetric evaluation set based on the FEVER (fact verification) dataset

Source code and notebooks to reproduce experiments and benchmarks on Bias Faces in the Wild (BFW).

How are words loaded with meaning? Repository to accompany research paper in preparation by Alina Arseniev-Koehler and Jacob G. Foster, titled "Machine learning as a model for cultural learning: teaching an algorithm what it means to be fat."

This is a collection of papers and other resources related to fairness.

Compass-aligned Distributional Embeddings. Align embeddings from different corpora

Chrome extension to show you the bias of websites you travel to.

This python script guesses the race and gender (probabilistically) of the first and last authors for papers in your citation list (in the form of a .bib file) and compares your list to expected distributions based on a model that accounts for paper characteristics (e.g., author location, author seniority, journal, et cetera.) unrelated to race and gender.

Source code and dataset for the paper "Can Fine-tuning Pre-trained Models Lead to Perfect NLP? A Study of the Generalizability of Relation Extraction"

Basic sensitivity analysis of epidemiological results in R

Privy filter is made to give the method for removing/accommodating for unethical bias in data.

Find here the analysis of the data for the experiment when an unconscious preference is happening in real time