jmrinaldi's repositories
sagemaker-distributed-training-workshop
Hands-on workshop for distributed training and hosting on SageMaker
graphein
Protein Graph Library
alphafold
Open source code for AlphaFold.
pyprobml
Python code for "Probabilistic Machine learning" book by Kevin Murphy
google-research
Google Research
deepmind-research
This repository contains implementations and illustrative code to accompany DeepMind publications
symbolic_rxn
Integrating Deep Neural Networks and Symbolic Inference for Organic Reactivity Prediction
kaggle-rcic-1st
1st Place Solution for Kaggle Recursion Cellular Image Classification Challenge -- https://www.kaggle.com/c/recursion-cellular-image-classification/
DeepExplain
A unified framework of perturbation and gradient-based attribution methods for Deep Neural Networks interpretability
genomelake
Simple and efficient access to genomic data for deep learning models.
convex_adversarial
A method for training neural networks that are provably robust to adversarial attacks.
TCN
Sequence modeling benchmarks and temporal convolutional networks
dragonn
A toolkit to learn how to model and interpret regulatory sequence data using deep learning.
draft-class-defenders-ml
Using machine learning to predict the best defenders in the 2018 draft class
finetune-transformer-lm
Code and model for the paper "Improving Language Understanding by Generative Pre-Training"
sentiment-discovery
Unsupervised Language Modeling at scale for robust sentiment classification
tybalt
Training and evaluating a variational autoencoder for pan-cancer gene expression data
UNIT
Unsupervised Image-to-Image Translation
deep-retina
deep-retina is a project to build a convolutional neural network that can predict retinal ganglion cell responses to natural stimuli with high accuracy.
nucleus
Python and C++ code for reading and writing genomics data.
chess-alpha-zero
Chess reinforcement learning by AlphaGo Zero methods.
Keras-GAN-1
Keras implementations of Generative Adversarial Networks.
ML-epitopes-prediction
This repository describe the usage of neural networks to predict the affinity of peptides to MHC type I for humans. Neural networks was written in tensorflow and keras
keras-molecules
Autoencoder network for learning a continuous representation of molecular structures.
gans
Generative Adversarial Networks implemented in PyTorch and Tensorflow
pytudes
Python programs to practice or demonstrate skills.
tf-vqvae
Tensorflow Implementation of the paper [Neural Discrete Representation Learning](https://arxiv.org/abs/1711.00937) (VQ-VAE).