google / TrustScore
To Trust Or Not To Trust A Classifier. A measure of uncertainty for any trained (possibly black-box) classifier which is more effective than the classifier's own implied confidence (e.g. softmax probability for a neural network).
β175Updated 2 years ago
Alternatives and similar repositories for TrustScore:
Users that are interested in TrustScore are comparing it to the libraries listed below
- β125Updated 3 years ago
- β134Updated 5 years ago
- Using / reproducing ACD from the paper "Hierarchical interpretations for neural network predictions" π§ (ICLR 2019)β128Updated 3 years ago
- Codebase for "Deep Learning for Case-based Reasoning through Prototypes: A Neural Network that Explains Its Predictions" (to appear in AAβ¦β74Updated 7 years ago
- This repository contains the full code for the "Towards fairness in machine learning with adversarial networks" blog post.β117Updated 4 years ago
- Algorithms for abstention, calibration and domain adaptation to label shift.β36Updated 4 years ago
- This project contains code for paper Ksenia Konyushkova, Raphael Sznitman, Pascal Fua 'Learning Active Learning from Data', NIPS 2017β87Updated 2 years ago
- OD-test: A Less Biased Evaluation of Out-of-Distribution (Outlier) Detectors (PyTorch)β62Updated last year
- Tools for training explainable models using attribution priors.β123Updated 4 years ago
- β264Updated 5 years ago
- Keras implementation for DASP: Deep Approximate Shapley Propagation (ICML 2019)β61Updated 5 years ago
- Towards Automatic Concept-based Explanationsβ159Updated 11 months ago
- Code for using CDEP from the paper "Interpretations are useful: penalizing explanations to align neural networks with prior knowledge" htβ¦β127Updated 4 years ago
- code release for Representer point Selection for Explaining Deep Neural Network in NeurIPS 2018β67Updated 3 years ago
- An implementation of MixMatch with PyTorchβ36Updated 4 years ago
- Calibration library and code for the paper: Verified Uncertainty Calibration. Ananya Kumar, Percy Liang, Tengyu Ma. NeurIPS 2019 (Spotligβ¦β146Updated 2 years ago
- Experiments for AAAI anchor paperβ63Updated 7 years ago
- Supervised Local Modeling for Interpretabilityβ28Updated 6 years ago
- Code repository for our paper "Failing Loudly: An Empirical Study of Methods for Detecting Dataset Shift": https://arxiv.org/abs/1810.119β¦β104Updated last year
- Python codes for weakly-supervised learningβ123Updated 4 years ago
- A lightweight implementation of removal-based explanations for ML models.β59Updated 3 years ago
- Contains code for the NeurIPS 2019 paper "Practical Deep Learning with Bayesian Principles"β244Updated 5 years ago
- Gold Loss Correctionβ87Updated 6 years ago
- Combating hidden stratification with GEORGEβ63Updated 3 years ago
- This is a benchmark to evaluate machine learning local explanaitons quality generated from any explainer for text and image dataβ30Updated 3 years ago
- Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning.β238Updated 9 months ago
- This is a public collection of papers related to machine learning model interpretability.β26Updated 3 years ago
- Code/figures in Right for the Right Reasonsβ55Updated 4 years ago
- Code for "Evaluating Explainable AI: Which Algorithmic Explanations Help Users Predict Model Behavior?"β46Updated last year
- Code and data for the experiments in "On Fairness and Calibration"β51Updated 2 years ago