Keep track of whether you've read items in Zotero

Interpretability for sequence generation models 🐛 🔍

The official Meta Llama 3 GitHub site

A Python package for modular causal inference analysis and model evaluations

Install and Run Python Applications in Isolated Environments

A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.

Attributing predictions made by the Inception network using the Integrated Gradients method

PyTorch implementation of the Quasi-Recurrent Neural Network - up to 16 times faster than NVIDIA's cuDNN LSTM

A very simple framework for state-of-the-art Natural Language Processing (NLP)

Combining encoder-based language models

Modern scheduling library for Python

A CoNLL-U parser that takes a CoNLL-U formatted string and turns it into a nested python dictionary.

Training RNNs as Fast as CNNs (https://arxiv.org/abs/1709.02755)

A simple example of creating a python module using C or C++ code

An eXplainable AI toolkit with Concept Relevance Propagation and Relevance Maximization

Code and data for paper Colorless Green Recurrent Networks Dream Hierarchically

Using C in Python (A quick introduction)

Code for the paper "Evaluating Attribution Methods using White-Box LSTMs."

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

Layer-wise Relevance Propagation (LRP) for LSTMs.

Tigramite is a python package for causal inference with a focus on time series data. The Tigramite documentation is at

Die wichtigsten APIs Deutschlands in einem Python Paket.

Model interpretability and understanding for PyTorch

Implementation of character based convolutional neural network

Tensorflow implementations of Text Classification Models.

😈Awful AI is a curated list to track current scary usages of AI - hoping to raise awareness

Learning Convolutional Neural Networks with Interactive Visualization.

Audio processing by using pytorch 1D convolution network