Zennit is a high-level framework in Python using PyTorch for explaining/exploring neural networks using attribution methods like LRP.

A PyTorch 1.6 implementation of Layer-Wise Relevance Propagation (LRP).

A basic implementation of Layer-wise Relevance Propagation (LRP) in PyTorch.

使用LSTM及股票因子数据预测未来收益，使用LRP(layer-wise relevance propagation)增强网络可解释性

[ECCV 2022: Oral] In this work, we discover that color is a crtical transferable forensic feature (T-FF) in universal detectors for detecting CNN-generated images.

An XAI library that helps to explain AI models in a really quick & easy way

Explain Neural Networks using Layer-Wise Relevance Propagation and evaluate the explanations using Pixel-Flipping and Area Under the Curve.

Transfer Explainability via Layer-Wise Relevance Propagation Demo for AAAI

Repository for the 'best student paper award' winning paper at the IEEE 35th International Symposium on Computer Based Medical Systems (CBMS 2022), Exploring LRP and Grad-CAM visualization to interpret multi-label-multi-class pathology prediction using chest radiography, Mahbub Ul Alam, Jón Rúnar Baldvinsson and Yuxia Wang. https://doi.org/10.11…

Repository for the journal article 'SHAMSUL: Systematic Holistic Analysis to investigate Medical Significance Utilizing Local interpretability methods in deep learning for chest radiography pathology prediction'

Briefly introduce methods of explainable ai in LLM

(Master's Thesis) Alam, Mahbub Ul, From Speech to Image: A Novel Approach to Understand the Hidden Layer Mechanisms of Deep Neural Networks in Automatic Speech Recognition, Masterarbeit, Institut für Maschinelle Sprachverarbeitung, Universität Stuttgart, 2017. (https://www.ims.uni-stuttgart.de/en/research/publications/theses/)

ECQx: Explainability-Driven Quantization for Low-Bit and Sparse DNNs