Iaroslav Omelianenko's Projects
The algorithm to build data model describing antigen - molecule reaction
Go client for AMQP 0.9.1
Converter of Android string resources file to CSV in order to have it for external translations
The converter of Android strings resources to iOS Localisable.strings
A packaged and slightly-modified version of https://github.com/bbitmaster/ale_python_interface
Open-source software for urban autonomous driving
The classic Bomber Man game with Reinforcement Learning based AI agent for J2ME platform. It was done long before RL become so hypo :)
Its an attempt to create Brain Hash Algorithm able to find robust distinction between EEG signals of different humans
The simple captcha cracker in GO
This is simple chatbot application with Natural Language Understanding to maintain very simple shopping list
The algorithm to build data model for child stuntedness prediction based on specific set of medical records
π₯ A tool for visualizing and tracking your machine learning experiments. This repo contains the CLI and Python API.
Convolutional Neural Networks
A torch implementation of http://arxiv.org/abs/1511.06434
The Deep Neuroevolution GPU enhanced with integrated Atari ALE environment
Deep Neuroevolution
The collection of utilities to work with QFrame implementation of the data frames in GO language (joins, etc)
Docker registry cli tool, primarily for deleting images.
The image classification with Convolutional Neural Networks using MXNet library for Deep Learning
Reimplementation of Deep Recurrent Attentive Writer (DRAW) network architecture.
The experiment with applying NLP to correction of definite/indefinite articles in English text corpus
This is iOS application based on Reference iOS Sender: CastVideos-ios application from Google. This application is able to cast videos found at ex.ua online video hosting. NB: the ex.ua video hosting is dead now - the application only for references.
A framework for photorealistic hardware-in-the-loop agile flight simulation using Unity3D and ROS. Developed by MIT FAST Lab.
Former is a fully customizable Swift2 library for easy creating UITableView based form.
starter from "How to Train a GAN?" at NIPS2016
The implementation of evolvable-substrate HyperNEAT algorithm in GO language. ES-HyperNEAT is an extension of the original HyperNEAT method for evolving large-scale artificial neural networks.
The GraphML support for GO language
The GOLang implementation of NeuroEvolution of Augmented Topologies (NEAT) method to evolve and train Artificial Neural Networks without error back propagation
This project provides GOLang implementation of Neuro-Evolution of Augmenting Topologies (NEAT) with Novelty Search optimization aimed to solve deceptive tasks with strong local optima