Alex Rogozhnikov's Projects
Raymarching neural network in browsers with WebGL shaders
AdamW optimizer for bfloat16 models in pytorch 🔥.
A lightweight library to build and train Deep Reinforcement Learning agents using Theano+Lasagne
'Brilliantly wrong' blog, Machine Learning visualizations live here
Test of algorithms on highly-categorical data
Cellxgene Gateway allows you to use the Cellxgene Server provided by the Chan Zuckerberg Institute (https://github.com/chanzuckerberg/cellxgene) with multiple datasets.
NumPy & SciPy for GPU
Yet another (very simple) approach for adversarial training.
Reliable, scalable, efficient demultiplexing for single-cell RNA sequencing
Genetic multiplexing of barcoded single cell RNA-seq
Multidimensional indexing for tensors
Flexible and powerful tensor operations for readable and reliable code (for pytorch, jax, TF and others)
FakeLeptons recognition for CMS experiment
:wavy_dash::earth_africa::wavy_dash: Analyse GW150914 (gravitational waves)
Machine Learning for High Energy Physics.
Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia, Scala, Go, Javascript and more
InfiniteBoost: building infinite ensembles with gradient descent
Extremely simplistic viewer of small ndimensional patches for jupyter notebook. Powered by einops
Implementation of Kronecker Attention in Pytorch
attempt to update openfold code to make it installable in 2024. Dropping binaries
Minified version of ANARCI, pip-installable
minified, pip-installable version of DockQ metric
Multi-modal Content Creation Model Training Infrastructure including the FACT model (AI Choreographer) implementation.
Machine Learning session on Grad Days at Heidelberg university 2017
Materials for the course of machine learning at Imperial College organized by YSDA
Materials for the course of machine learning at Imperial College organized by YSDA
MLHEP 2016 materials
An All-MLP solution for Vision, from Google AI