Aletheia

ReLU unwrapper

A tool to explain complex neural networks by unwrapping their ReLU layers

A Python package for unwrapping ReLU DNNs

GitHub

71 stars
7 watching
20 forks
last commit: about 1 year ago
deep-neural-networksexplainable-ailocal-interpretationlocal-linear-modelsself-explanatory-ml

Related projects:

Repository Description Stars
dnouri/nolearn Provides a Python interface to integrate neural networks with scikit-learn, making it easier to use deep learning libraries like Lasagne. 949
selfexplainml/piml-toolbox A Python toolbox for developing and diagnosing interpretable machine learning models with low-code and high-code APIs. 1,221
deel-ai/xplique An Explainable AI toolbox that provides various methods and tools to understand and interpret the behavior of neural networks 654
ethliup/deepunrollnet A deep learning network designed to correct rolling shutter distortions in images 46
vlfeat/autonn An API wrapper around MatConvNet that adds automatic differentiation for easy deep learning prototyping and research 89
lxtgh/omg-seg Develops an end-to-end model for multiple visual perception and reasoning tasks using a single encoder, decoder, and large language model. 1,336
sandeep42/anuvada This is an open source PyTorch library providing tools and models to explain the predictions of deep neural networks for natural language processing tasks. 19
blent-ai/alepython An ALE plot generation tool for explaining machine learning model predictions 160
uxmal/reko A binary decompiler that analyzes and reverse-engineers machine code binaries from various processor architectures. 2,173
mahaloz/daila Decomposition and AI interface tool 566
rentruewang/koila A lightweight wrapper around PyTorch to prevent CUDA out-of-memory errors and optimize model execution 1,823
molcik/python-neuron A Python library for implementing and training various neural network architectures 40
nikitakit/self-attentive-parser An NLP parser with high accuracy models for multiple languages 873
google-deepmind/einshape A unified reshaping library for JAX and other frameworks. 100
ethicalml/xai An eXplainability toolbox for machine learning that enables data analysis and model evaluation to mitigate biases and improve performance 1,135