Name: Boris Piakillia
Type: User
Company: © 200k BP Homo sapiens sapiens
Bio: I am a Machine Learning researcher with a passion to use Artificial Intelligence in Life sciences and making people's lives better 👨💻❤️
Twitter: morphysm
Location: The Universe, Local group, Milky Way, Solar system, Earth
Boris Piakillia's Projects
OpenAI Baselines: high-quality implementations of reinforcement learning algorithms
Bullet Physics SDK: real-time collision detection and multi-physics simulation for VR, games, visual effects, robotics, machine learning etc.
A Keras implementation of CapsNet in NIPS2017 paper "Dynamic Routing Between Capsules". Now test error = 0.34%.
Implementation of the Paper "Learning Continuous and Data-Driven Molecular Descriptors by Translating Equivalent Chemical Representations" by Robin Winter, Floriane Montanari, Frank Noe and Djork-Arne Clevert.
Multi-layer Recurrent Neural Networks (LSTM, GRU, RNN) for character-level language models in Torch
Message Passing Neural Networks for Molecule Property Prediction
Materials for deep NLP course
ECG classification programs based on ML/DL methods
Multi-agent reinforcement learning programs based on Game theory
My ML examples
This repository contains the scripts about GAN implementation in Python
Deep Learning library for Python. Runs on TensorFlow, Theano, or CNTK.
Keras implementations of Generative Adversarial Networks.
An open set of tools for automating tasks relating to small molecules
Implementation of Reinforcement Learning Algorithms. Python, OpenAI Gym, Tensorflow. Exercises and Solutions to accompany Sutton's Book and David Silver's course.
Морфологический анализатор на основе нейронных сетей и pymorphy2
For RNN use
Training RNNs as Fast as CNNs (https://arxiv.org/abs/1709.02755)
For collaboration with students
Fast parallel CTC.
Automatic extraction of edited sentences from text edition histories.