Search Results for "learn"

...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 opening patterns and endgame tactics beyond simple pattern libraries. The codebase includes tools for parsing classic Go formats, generating training examples, and evaluating models on standard test suites and online servers. A KGS/online client and match runner make it practical to stage controlled tournaments or continuous rating evaluation. ...

TexLexAn is an open source text analyser for Linux, able to estimate the readability and reading time, to classify and summarize texts. It has some learning abilities and accepts html, doc, pdf, ppt, odt and txt documents. Written in C and Python.

dbacl is a general purpose digramic Bayesian text classifier. It can learn text documents you provide, and then compare new input with the learned categories. It can be used for spam filtering, or within your own shell scripts. Sometimes it plays che

SimpleAiBot is created for educational purposes but it can grow out to something much bigger, however still educational. This project exists so other people can actually look at the code of a working chat bot and learn from it or even improve SimpleAiBot! If you're looking for this: this is it! Also don't hesitate to join and improve SimpleAiBot, better make your changes public and usable to everyone then experimenting on your own. PS: More experienced AI developers are also welcome to learn others how AI works!

We experiment with Evolution of Artifical Neural Networks, combining the two fields of Evolutionary Computation and ANNs. Our methods are applied to a variety of interesting problems. To learn more, click on "Home Page", "Mail", or "Files".

HOPEN (Hopfield Open Network) is a program for patterns recognition based on a Hopfield Artificial Neural Network. It can learn using Hebb's Rule, Iterative Learning Scheme and Repeated Hebbian Learning.

An object-oriented platform and algorithms for the game of GO. Aims: 1) A capable engine that can learn through experience. 2) A re-usable algorithmic framework for rapid development of new GO-playing engines.

Project Genesis brings the game of life up-to-date. instead of dots, we have animals, instead of trivial rules about close proximity dots, we model real world activities: move,eat,kill,steal,destroy,sleep, breed and learn different patterns of behavior.

ECTOR is a multilingual chatterbot able to learn from users' entries.

CompLearn is a general-purpose compression-based machine learning system that uses data compression to learn or data mine patterns in arbitrary data.

MegaHAL is a 'conversation simulator' that learns as you talk to it. MegaHAL differs from conversation simulators such as Eliza in that it uses a Markov Model to learn how to hold a conversation. It is possible to teach MegaHAL to talk about new topic

The Sh.I.A. project aims to develop a chatterbot (like Jabberwacky) that can learn whatever you teach it. This is oriented to novel developers and enthusiasts (like me :))who want to learn about A.I..

The goal of this project is to learn about and develop an AI. Current path is using a bot on AIM.

An AI program which uses a 3d environment to learn objects and concepts. Elyse has no initial language database, but learns language dynamically.