Category Archives: Coding

iChess.io Now Open Source – Version 12.27 Released

Posted on by — Leave a reply

iChess.io – The open AI chess platform for Classic and Chess960 Introduction After several years of research and development in GPU computing, Monte Carlo Tree Search (MCTS), and evaluation algorithms, I am proud to announce that iChess.io is now officially open source on GitHub. The project merges classical and Fischer Random Chess (Chess960) into a single adaptive platform powered by AI, self-learning, and real-time evaluation. It has been designed for developers, researchers, and chess enthusiasts who want to explore how modern chess engines think, evolve, and learn. 🔗 GitHub Repository: github.com/sowson/ichess.io 🌐 Live Demo: iChess.io  •  🎲 3D Version: 3d.iChess.io Continue ReadingiChess.io Now Open Source – Version 12.27 Released→

iChess.io Final Design

Posted on by — Leave a reply

Hi, today I want to share the architecture of the PhD project that took me about three years. It is a perfectly tuned combination of C/C++/C#/TS/JS programming languages. To make the comprehensive solution for Classic and Random/Fisher/960 Chess, you may wonder what took me so long. First of all, I wanted to use Darknet on OpenCL in C/C++, and I achieved only a 1MB file of CNN machine learning weights. I also participate in all layers of Open Source projects on GitHub. Starting from a community-made solution and supported by AMD and the Open Source community, clBLAS for MultiGPU is Continue ReadingiChess.io Final Design→

Free Correctly MCTS in C in the iChess.io

Posted on by — Leave a reply

Hi, today I would like to show you issue I faced for a long time… I wanted to use Monte Carlo Tree Search with classic select, expand, back propagate and so on… the problem I faced was the memory leak, and I was looking for some time to good solution to reduce memory by one level and efficnet free memory. To make it correclty you have to calculate max depth and reecude from deeper to less deeper in order the tree. Rest is explain below in the code example. Thanks and Enjoy! :D.

C and Track Memory

Posted on by — Leave a reply

Hi, today I would like to share a bit one solution that makes me happy on macOS and C programming. Tracking allocated memory to look for memory leaks. It is very careful and quite detailed finds missing memory. It also can be very ellegant disabled by commented out definition of enable it. Maybe not like Valgrind on Linux but for me on macOS is super cool. Enjoy! Thanks!

iChess.io Architecture

Posted on by — Leave a reply

Hi, my Dear Readers! ;-). Let me start Today’s story with the fact that the iChess.io starts to play Chess and Chess 960 as well ;-). Without that start statement, any design advantages do not make sense. Please remember that any good architectural design is about how things work, not how things are built. I heard that once, and it made an impression on me. It turns out a clear understanding that it is all about non-functional aspects at the beginning and the end by the functional experience. So, you may ask how to start with architecture design if you Continue ReadingiChess.io Architecture→

iChess.io v2.27

Posted on by — Leave a reply

This is a day, I was looking forward entire year. I remember the moment when we discuss with Professor Jacek Izydorczyk the subject of math oriented AI that can be very enjoyable and valuable, the Game of Kings. But first, we considered to reaserch AI in the medical aspects of usage, the financial, and then I told that the best in class AI is for gaming but the only game I am able cannot be complex like such amazing strategy I love, The Settlers New Alliance where only map editor is missing… ;-). We wanted to keep in mind usage Continue ReadingiChess.io v2.27→

The iChess.io v1.27 is Ready to Play Publicly with Reinforcement Learning ;-)

Posted on by — Leave a reply

Hi, it has been some time since the last entry on this blog… ;-). I almost forget how nice it is to write a blog post in the middle of the night with AirPods music :P. Truth be told, I almost dropped this iChess.io project once on the aiChess.io I could not make sufficient working self-learning of the chess. I do not want to use any books on chess, only, like they say, reinforcement learning. So I did at last ;-). There are many things I have learned since this project started about 6 months ago. And I have to Continue ReadingThe iChess.io v1.27 is Ready to Play Publicly with Reinforcement Learning 😉→

iChess.io Project Ready to Play

Posted on by — Leave a reply

Hi, today I want to share the project iChess.io I have been working on for some time. And invite you to play 😉 With AI with Graphics Card acceleration in short GPU acceleration to make each move at least 5 seconds by the game engine. It is a self-study solution that will be stronger after each game, but each game a bit :D. You may see the below video that shows almost the weakest engine you can imagine that “studies” the game strategy. In fact, there is, in my opinion, the best strategy invited ever. Why did I do it? Continue ReadingiChess.io Project Ready to Play→

Darknet on OpenCL on FreeBSD 13.1

Posted on by — Leave a reply

Hi, recently I helped a bit for a GitHub user rajhlinux. I am not sure if you are familiar with this Operation System. I am only a bit. But the beauty of C and C++ is that it works on different OSes and works fast! Below cute daemon image is from Wikipedia, and you can click on it to learn more. This user, a fan of FreeBSD, was using version 13.1 and made a ( downloads) for Darknet on OpenCL repository. Thank you for this work, and wish this user the best of luck with Computer Vision! ;-). Also, I Continue ReadingDarknet on OpenCL on FreeBSD 13.1→