kuleshov/architect

Stars
20
Rank 1,121,974 (Top 23 %)
Language
Python
Created about 11 years ago
Updated about 8 years ago

kuleshov/architect

kuleshov

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Scaffolding genomes using synthetic long read clouds

audio-super-res

Audio super resolution using neural networks

teaching-material

Teaching materials for the machine learning and deep learning classes at Stanford and Cornell

Jupyter Notebook

cornell-cs5785-2020-applied-ml

Teaching materials for the applied machine learning course at Cornell Tech (online edition)

Jupyter Notebook

minillm

MiniLLM is a minimal system for running modern LLMs on consumer-grade GPUs

cornell-cs5785-2023-applied-ml

Lecture materials for Cornell CS5785 Applied Machine Learning (Fall 2023)

Jupyter Notebook

tf-wgan

Wasserstein DCGAN in Tensorflow/Keras

gwaskb

Machine-curated database of genetic disease and genome-wide association studies

Jupyter Notebook

tensor-factorization

Tensor Factorization via Matrix Factorization

cs228-notes

Lecture notes on probabilistic graphical modeling, based on Stanford CS228 (work in progress!)

online-learning

A few basic online learning algorithms

deep-learning-models

Implementations of popular deep learning models in Theano+Lasagne

deep-hybrid-models

Deep hybrid models: bridging discriminative and generative approaches https://cs.stanford.edu/~ermon/papers/uai2017_cr.pdf

neural-variational-inference

Neural variational inference and learning in undirected graphical models http://www.stanford.edu/~kuleshov/papers/nips2017.pdf

generalized-rayleigh-quotient

Fast algorithms for sparse principal component analysis

ProbHap

Probabilistic single-individual haplotyping

prism

Statistical phasing software for long read data

convolutional-draw

Tensorflow implementation of Convolutional DRAW by Gregor et al. (2016)

lens

Variant calling and haplotyping algorithm optimized for synthetic long reads

nanoscope

Metagenomic analysis pipeline aimed at synthetic long reads

dotfiles

scripts

Various short scripts I wrote for my work

pixelcnn-pp-experiments