Search Results for "artificial neural network code"

darkforestGo is an early deep-reinforcement-learning Go engine that combined a convolutional policy/value network with Monte Carlo Tree Search (MCTS) to play the full 19×19 game at a strong amateur level. The system couples fast GPU policy inference with CPU or GPU-assisted tree search so priors from the network guide exploration while search refines local tactics. Training pipelines mix supervised learning from human professional games and self-play fine-tuning, allowing the model to learn...

Self chess learning process by artificial neural network white random attribution to of values of chess game, before to pass opposed value to neural network and the desire successor of board with various part of game chess generated with minimax algorithm.

JAS is a java library for creating agent based simulations. It features a discrete-event time engine, APIs for network simulation design, powerful yet easy-to-use implementations of Genetic Algorithms and Neural Networks.

AlizaGameAPI is a robust, open-source Java-based framework designed to streamline and enhance the development of 2D and 3D games. It offers a comprehensive set of tools, utilities, and libraries, empowering developers to create immersive and dynamic gaming experiences with ease. Key Features: Modular Architecture, Rich Graphics and UI Components, Comprehensive Game Logic and Character Management, Environment and World-Building Tools, Statistical and Mathematical Utilities, Enhanced...

Turn-based strategy game for developers/technical experienced users, based on neural networks, algorithmic programming languages and other techniques.

RL Poker is a study project Java implementation of an e-soft on-policy Monte Carlo Texas Hold'em poker reinforcement learning algoritm with a feedforward neural network and backpropagation. It provides a graphical interface to monitor game rounds.

Zeus is a small, lightweight, very fast object oriented framework for developing neural networks with an integrated shell interface.

Network gaming environment for AI warriors. Offers an application server, a soccer game application, an observer module visualizing a match and a template code for the warriors development.

A java based neural network framework. The Auratus network is built around an XML messaging system, allowing for a complete MVC design. Additionally, Auratus networks are constructed and at the node/edge level, allowing for advanced topologies.

Multilayer neural network sudoku generator that can be trained to produce puzzles with different degree of dificulty and imitate those made by people.

Sourceforge is no longer being updated! This project has merged into another that can be found here: https://github.com/nicrohobak/Toolbox The designer portion is currently on hold. ------------------------------------------------------------ A C++ neural network toolkit. This project is a C++ library for adding, potentially complicated, neural networks to any project. libNervousSystem is developed in conjunction with the GUI tool, Nervous System Designer, to easily generate...

VelbazhdGo is BOINC distributed computing project for training Artificial Neural Networks (ANN), by using Genetic Algorithms (GA), to play the popular game Go.