deel-ai / influenciaeLinks
👋 Influenciae is a Tensorflow Toolbox for Influence Functions
☆65Updated last week
Alternatives and similar repositories for influenciae
Users that are interested in influenciae are comparing it to the libraries listed below
Sorting:
- Build and train Lipschitz constrained networks: TensorFlow implementation of k-Lipschitz layers☆102Updated 10 months ago
- Simple, compact, and hackable post-hoc deep OOD detection for already trained tensorflow or pytorch image classifiers.☆60Updated 2 weeks ago
- ☆38Updated 4 months ago
- New implementations of old orthogonal layers unlock large scale training.☆29Updated 4 months ago
- 👋 Xplique is a Neural Networks Explainability Toolbox☆731Updated last week
- MetaQuantus is an XAI performance tool to identify reliable evaluation metrics☆40Updated last year
- pyDVL is a library of stable implementations of algorithms for data valuation and influence function computation☆142Updated 2 weeks ago
- OpenXAI : Towards a Transparent Evaluation of Model Explanations☆252Updated last year
- 👋 Code for the paper: "Look at the Variance! Efficient Black-box Explanations with Sobol-based Sensitivity Analysis" (NeurIPS 2021)☆33Updated 3 years ago
- 👋 Puncc is a python library for predictive uncertainty quantification using conformal prediction.☆370Updated last week
- Zennit is a high-level framework in Python using PyTorch for explaining/exploring neural networks using attribution methods like LRP.☆239Updated this week
- Wrapper for a PyTorch classifier which allows it to output prediction sets. The sets are theoretically guaranteed to contain the true cla…☆255Updated 3 years ago
- An eXplainable AI toolkit with Concept Relevance Propagation and Relevance Maximization☆140Updated 3 weeks ago
- 💡 Adversarial attacks on explanations and how to defend them☆334Updated last year
- Quantus is an eXplainable AI toolkit for responsible evaluation of neural network explanations☆636Updated 2 weeks ago
- A fairness library in PyTorch.☆32Updated last year
- XAI-Bench is a library for benchmarking feature attribution explainability techniques☆70Updated 3 years ago
- Uncertainty Quantification 360 (UQ360) is an extensible open-source toolkit that can help you estimate, communicate and use uncertainty i…☆268Updated 4 months ago
- Calibration library and code for the paper: Verified Uncertainty Calibration. Ananya Kumar, Percy Liang, Tengyu Ma. NeurIPS 2019 (Spotlig…☆152Updated 3 years ago
- A toolkit for quantitative evaluation of data attribution methods.☆55Updated 6 months ago
- Reliability diagrams visualize whether a classifier model needs calibration☆165Updated 3 years ago
- 👋 Overcomplete is a Vision-based SAE Toolbox☆118Updated 2 months ago
- CARLA: A Python Library to Benchmark Algorithmic Recourse and Counterfactual Explanation Algorithms☆298Updated 2 years ago
- LENS Project☆52Updated last year
- 👋 Code for : "CRAFT: Concept Recursive Activation FacTorization for Explainability" (CVPR 2023)☆71Updated 2 years ago
- scikit-activeml: A Comprehensive and User-friendly Active Learning Library☆183Updated this week
- 🐟 CODS - Conformal Object Detection and Segmentation☆20Updated last month
- Model-agnostic posthoc calibration without distributional assumptions☆42Updated 2 years ago
- CausalPFN: Amortized Causal Effect Estimation via In-Context Learning☆87Updated last month
- An amortized approach for calculating local Shapley value explanations☆105Updated 2 years ago