kudkudak Goto Github PK

asteroid-challenge

Submission for NASA AsteroidChallenge

autoencoder-demo

Theano autoencoder demo for SeMPowisko 2014

bert

TensorFlow code and pre-trained models for BERT

buildbot_travis

Adaptors to make Buildbot more like travis

cleverhans

A library for benchmarking vulnerability to adversarial examples

common-sense-prediction

Common sense prediction using DL.

compound-activity-prediction

Code for TFML 2015 conference paper

dnn_sharpest_directions

Code for "On the Relation Between the Sharpest Directions of DNN Loss and the SGD Step Length", ICLR 2019

dogs-vs-cats

Repository for the IFT6266 course, winter 2015

dotfiles

Configuration files

edward

A library for probabilistic modeling, inference, and criticism. Deep generative models, variational inference. Runs on TensorFlow.

growing-neural-gas

Online, efficient GNG R package in C++

keras

Deep Learning library for Python. Convnets, recurrent neural networks, and more. Runs on Theano or TensorFlow.

kudkudak.github.io

Personal website

l4-optimizer

Code for paper "L4: Practical loss-based stepsize adaptation for deep learning"

learning-wordnet

Learning wordnet using tensor neural network

m1wrapper-python

Molecule One API Wrapper

mat

The official implementation of the Molecule Attention Transformer.

megan

Code for "Molecule Edit Graph Attention Network: Modeling Chemical Reactions as Sequences of Graph Edits"

mixup-cifar10

mixup: Beyond Empirical Risk Minimization

multinli

osprey

osprey is the plumbing for machine learning hyperparameter optimization.

python-ai-samples

Python AI/NLP samples

python-for-data-processing

Lab for Jagiellonian University course

pytorch

Tensors and Dynamic neural networks in Python with strong GPU acceleration

r2-learner

Code supporting "On certain limitations of Recursive Representation Models" paper

sacred

Sacred is a tool to help you configure, organize, log and reproduce experiments developed at IDSIA.

sfi2016-ml-workshop

Repository for workshops held @ SFI 2016

transformers

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

vs-utils

Virtual screening and cheminformatics utilities