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).
☆174Updated last year
Alternatives and similar repositories for TrustScore:
Users that are interested in TrustScore are comparing it to the libraries listed below
- Using / reproducing ACD from the paper "Hierarchical interpretations for neural network predictions" 🧠 (ICLR 2019)☆128Updated 3 years ago
- ☆132Updated 5 years ago
- Algorithms for abstention, calibration and domain adaptation to label shift.☆36Updated 4 years ago
- Code for using CDEP from the paper "Interpretations are useful: penalizing explanations to align neural networks with prior knowledge" ht…☆128Updated 3 years ago
- Implementation of Estimating Training Data Influence by Tracing Gradient Descent (NeurIPS 2020)☆224Updated 2 years ago
- A lightweight implementation of removal-based explanations for ML models.☆57Updated 3 years ago
- ☆264Updated 5 years ago
- ☆124Updated 3 years ago
- Codebase for "Deep Learning for Case-based Reasoning through Prototypes: A Neural Network that Explains Its Predictions" (to appear in AA…☆73Updated 7 years ago
- Keras implementation for DASP: Deep Approximate Shapley Propagation (ICML 2019)☆60Updated 5 years ago
- ☆49Updated 4 years ago
- Tools for training explainable models using attribution priors.☆120Updated 3 years ago
- Reusable BatchBALD implementation☆74Updated 10 months ago
- Code for the paper "Calibrating Deep Neural Networks using Focal Loss"☆158Updated last year
- code release for Representer point Selection for Explaining Deep Neural Network in NeurIPS 2018☆67Updated 3 years ago
- Calibration of Convolutional Neural Networks☆160Updated last year
- Toolkit for building machine learning models that generalize to unseen domains and are robust to privacy and other attacks.☆175Updated last year
- This is a public collection of papers related to machine learning model interpretability.☆25Updated 3 years ago
- Code repository for our paper "Failing Loudly: An Empirical Study of Methods for Detecting Dataset Shift": https://arxiv.org/abs/1810.119…☆102Updated 9 months ago
- Reliability diagrams, Platt's scaling, isotonic regression☆75Updated 10 years ago
- Contains code for the NeurIPS 2019 paper "Practical Deep Learning with Bayesian Principles"☆243Updated 5 years ago
- An implementation of MixMatch with PyTorch☆36Updated 3 years ago
- Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning.☆234Updated 7 months ago
- Contrastive Explanation (Foil Trees), developed at TNO/Utrecht University☆45Updated last year
- Combating hidden stratification with GEORGE☆62Updated 3 years ago
- A way to achieve uniform confidence far away from the training data.☆37Updated 3 years ago
- Calibration library and code for the paper: Verified Uncertainty Calibration. Ananya Kumar, Percy Liang, Tengyu Ma. NeurIPS 2019 (Spotlig…☆143Updated 2 years ago
- ☆110Updated 2 years ago
- Causal Explanation (CXPlain) is a method for explaining the predictions of any machine-learning model.☆130Updated 4 years ago