interpretability · GitHub Topics

shap

@shap

#计算机科学# A game theoretic approach to explain the output of any machine learning model.

翻译 - 一种解释任何机器学习模型输出的博弈论方法。

interpretability machine-learning deep-learning gradient-boosting shap shapley explainability

Jupyter Notebook22.91 k

13 天前

awesome-production-machine-learning

@EthicalML

#计算机科学# A curated list of awesome open source libraries to deploy, monitor, version and scale your machine learning

翻译 - 精选的优秀开源库列表，用于部署，监视，版本化和扩展您的机器学习

machine-learning mlops interpretability explainability responsible-ai deep-learning machine-learning-operations ml-ops ml-operations privacy-preserving

17.62 k

6 天前

pytorch-grad-cam

@jacobgil

#计算机科学# Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.

翻译 - 在Pytorch中为CNN和视觉变压器实现了许多类激活图方法。包括Grad-CAM，Grad-CAM ++，Score-CAM，Ablation-CAM和XGrad-CAM

deep-learning pytorch grad-cam visualizations interpretability interpretable-ai interpretable-deep-learning score-cam class-activation-maps vision-transformers

Python10.62 k

1 个月前

interpret

@interpretml

#计算机科学# Fit interpretable models. Explain blackbox machine learning.

翻译 - 拟合可解释的模型。说明黑匣子机器学习。

machine-learning interpretability gradient-boosting blackbox scikit-learn xai interpretml interpretable-machine-learning interpretable-ai transparency

C++6.3 k

3 天前

captum

@pytorch • Meta

Model interpretability and understanding for PyTorch

翻译 - PyTorch的模型可解释性和理解

interpretability interpretable-ai interpretable-ml feature-importance feature-attribution

Python4.94 k

1 天前

stellargraph

S T E L L A R@stellargraph

#计算机科学# StellarGraph - Machine Learning on Graphs

翻译 - StellarGraph-图上的机器学习

graphs machine-learning machine-learning-algorithms graph-convolutional-networks networkx geometric-deep-learning saliency-map interpretability heterogeneous-networks graph-neural-networks

Python2.95 k

7 个月前

shapash

@MAIF

#计算机科学# 🔅 Shapash: User-friendly Explainability and Interpretability to Develop Reliable and Transparent Machine Learning Models

翻译 - Shapash使机器学习模型透明且每个人都可以理解

python machine-learning explainability explainable-ml transparency ethical-artificial-intelligence shap lime interpretability

Jupyter Notebook2.74 k

25 天前

penzai

@google-deepmind • 谷歌公司

A JAX research toolkit for building, editing, and visualizing neural networks.

fine-tuning interpretability jax neural-networks visualization

Python1.37 k

7 个月前

pyreft

Stanford NLP@stanfordnlp

ReFT: Representation Finetuning for Language Models

interpretability reft representation-finetuning

Python1.16 k

17 天前

decision-forests

@tensorflow • 谷歌公司

#计算机科学# A collection of state-of-the-art algorithms for the training, serving and interpretation of Decision Forest models in Keras.

翻译 - 一组用于Keras中的决策林模型的训练，服务和解释的最新算法。

python machine-learning random-forest tensorflow ml decision-trees gradient-boosting interpretability decision-forest keras

Python660

11 天前

laser

@pratyushasharma

#大语言模型# The Truth Is In There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction

gpt-j interpretability laser llama2 llm llms model-compression transformers

Python370

4 个月前