A genetic algorithm applied to the popular game of snake.

Approximate Nearest Neighbors in C++/Python optimized for memory usage and loading/saving to disk

A C++ implementation of a Neural Network Structure.

Project for the lecture "Building Interactive Devices" (HCI2) at HPI Potsdam

Candidate for Udacity MLND Capstone

Creating a perception pipeline for the pr2 robot in simulation, to perform pick and place tasks

PROPhet is a code to integrate machine learning techniques with first-principles quantum chemistry approaches

Latte is a convolutional neural network (CNN) inference engine written in C++ and uses AVX to vectorize operations. The engine runs on Windows 10, Linux and macOS Sierra.

Extensible, High-Level C++ Neural Network API designed for maximum user-friendliness and little requirement for user's to need to know what's being done under-the-hood.

Adaptive Real-Time Object Detection System with HOG and CNN Features

this is a toy for training nlp & ocr relative task

General image classification tool with a Qt based frontend

This is a small header only implementation of a Artificial neural network using varadic templates and c++11. Look at example for directions... It's horribly implemented and writen while I was drunk. It's slow, inefficient and stupid.

Its MachineLearning Project which detects objects and scenarios in a given image

CNN architectures in C++

Solves the binary A XOR B problem using only perceptrons with threshold activation functions and the perceptron learning rule. Implemented in C++.

Implement machine learning algorithms from scratch

The report presents a ball on plate balancing system useful for various educational purposes. A touch-screen placed on the plate is used for ball's position sensing and two servomotors are employed for balancing the plate in order to control ball's Cartesian coordinates. Due to its complexity, multiple steps were taken to solve the design challe…

AROW++ An implementation of the efficient confidence-weighted classifier

Classification is made in 2-dimensional space with artificial neural networks learning rules. Perceptron and Delta learning rules are implemented in different layers.