hierarchical-dnn-interpretations

Neural Explanation Tools

Provides an implementation of Hierarchical explanations for Neural Network predictions

Using / reproducing ACD from the paper "Hierarchical interpretations for neural network predictions" 🧠 (ICLR 2019)

GitHub

125 stars
9 watching
22 forks
Language: Jupyter Notebook
last commit: about 3 years ago
acdaiartificial-intelligenceconvolutional-neural-networksdata-sciencedeep-learningdeep-neural-networksexplainabilityexplainable-aifeature-importanceiclrinterpretabilityinterpretationjupyter-notebookmachine-learningmlneural-networkpythonpytorchstatistics

Related projects:

Repository Description Stars
understandable-machine-intelligence-lab/quantus An eXplainable AI toolkit for evaluating and interpreting neural network explanations in various deep learning frameworks. 556
dianna-ai/dianna A Python package providing an explainable AI interface to research projects 48
namisan/mt-dnn A PyTorch package implementing multi-task deep neural networks for natural language understanding 2,238
tensorflow/tcav An interpretability method that provides explanations for neural network predictions by highlighting high-level concepts relevant to classification tasks. 632
deel-ai/xplique An Explainable AI toolbox that provides various methods and tools to understand and interpret the behavior of neural networks 644
hyeongseokson1/cnn_deconvolution Improves deconvolution performance using a Convolutional Neural Network 22
ahmedfgad/numpycnn An implementation of a convolutional neural network (CNN) using NumPy for basic classification tasks. 570
doonny/pipecnn A tool for accelerating convolutional neural networks on Field-Programmable Gate Arrays (FPGAs) using OpenCL-based hardware design 1,253
marcoancona/deepexplain A framework for understanding how deep neural networks process input data to produce output 734
100/cranium A lightweight, portable C implementation of a feedforward artificial neural network library 592
microsoft/archai Automates the search for optimal neural network configurations in deep learning applications 467
nv-tlabs/gscnn This code implements a neural network architecture designed to perform semantic segmentation in computer vision tasks. 920
datamllab/xdeep Provides tools for interpreting deep neural networks 42
hagaygarty/mdcnn A 3D convolutional neural network framework supporting volumetric inputs and various features like dropout and batch normalization. 52
conan7882/googlenet-inception An implementation of a deep neural network architecture for image classification using pre-trained models and fine-tuning on the CIFAR-10 dataset. 282