A comprehensive set of fairness metrics for datasets and machine learning models, explanations for these metrics, and algorithms to mitigate bias in datasets and models.

Python code for training fair logistic regression classifiers.

Crop/Weed Field Image Dataset

A library that implements fairness-aware machine learning algorithms

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

Unsupervised (Self-Supervised) Clustering of Seismic Signals Using Deep Convolutional Autoencoders

A collection of news articles, books, and papers on Responsible AI cases. The purpose is to study these cases and learn from them to avoid repeating the failures of the past.

List of references about Machine Learning bias and ethics

Fair ML in credit scoring: Assessment, implementation and profit implications

R package for computing and visualizing fair ML metrics

This collection of codes can be used for extracting features from continuous seismic signals for different machine learning tasks.

Report.it è un applicativo Android/iOS sviluppato per lottare contro qualsiavoglia forma di discriminazione.

How Facebook and Google skew the distribution of advertisements, absent any targeting from the advertiser

Classifying hate speech with deep learning (honors thesis 2017-18)

This is a high discrimination scanner designed to recognise DNA motifs within a long stretch of DNA. Most importantly, this implementation shows how to implement a variable sensitivity for detection, by modifying the pseudocount values.

Matlab toolbox to integrate normal (Gaussian) distributions in any dimensions with any parameters in any domain, compute pdf/cdf/inverse cdf of any function of a normal vector, and measures of classification performance among two or more multinormals, like error matrix and d'.

Visualisation of data from a study into author gender representation at audio engineering conferences

This is a scanner designed to recognise DNA motifs within a long stretch of DNA. It uses two models for discrimination, one model representing the target and the second model representing the background.

Workshop with readings and exercises on the politics of tech.