Stars
An implementation of demixed Principal Component Analysis (a supervised linear dimensionality reduction technique)
A library for experimenting with, training and evaluating neural networks, with a focus on adversarial robustness.
PyTorch implementation of the NIPS-17 paper "Poincaré Embeddings for Learning Hierarchical Representations"
Google DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo.
Seminar on Advanced Topics in Theoretical Neuroscience - Columbia University 2019
Seminar on Advanced Topics in Theoretical Neuroscience - Columbia University 2020
A library for easy and efficient manipulation of tensor networks.
cmix is a lossless data compression program aimed at optimizing compression ratio at the cost of high CPU/memory usage.
PyTorch implementation of LeNet-5 with live visualization
This is the PyTorch implementation of VGG network trained on CIFAR10 dataset
A toolkit for evaluating the linguistic knowledge and transferability of contextual representations. Code for "Linguistic Knowledge and Transferability of Contextual Representations" (NAACL 2019).
Simple transformer implementation from scratch in pytorch.
An annotated implementation of the Transformer paper.
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
A PyTorch implementation of the Transformer model in "Attention is All You Need".
A repository containing tutorials for practical NLP using PyTorch
Code for the paper "On First-Order Meta-Learning Algorithms"
deep-retina is a project to build a convolutional neural network that can predict retinal ganglion cell responses to natural stimuli with high accuracy.
Materials for RNN tutorial @ Harvard-MIT Theoretical and Computational Neuroscience Journal Club
Tutorial for video classification/ action recognition using 3D CNN/ CNN+RNN on UCF101
Speech Recognition using DeepSpeech2.
Code for the paper "Language Models are Unsupervised Multitask Learners"
A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.
DeepSpeech is an open source embedded (offline, on-device) speech-to-text engine which can run in real time on devices ranging from a Raspberry Pi 4 to high power GPU servers.
End-to-end speech recognition using TensorFlow