During the last 12 years we have closely followed the evolution of Artificial Intelligence in chess; especially after the release of Stockfish in 2008 the chess engine’s strength developed very fast year by year. Stockfish dominated the computer chess tournaments, mainly fighting against Komodo and Houdini for the “best chess engine of the world title”. However, a chess revolution started in December 2017, Stockfish 8 was used as a benchmark to test Google division Deepmind’s AlphaZero, with each engine supported by different hardware.
AlphaZero is an Artificial Intelligence using a Neural Network System. This program trained through self-play for a total of nine hours and reached Stockfish’s level after just four. In 100 games from the normal starting position, AlphaZero won 25 games as White, won 3 as Black, and drew the remaining 72, with 0 losses.
The Alpha Zero approach inspired the chess engine developers and they quickly started to implement the neural network idea to their programs. In January 2018 the Leela Chess Zero project was first announced on TalkChess.com, a program inspired by Alpha Zero, but available for everyone. This revealed Leela Chess Zero as the open-source, self-learning chess engine to create a strong chess engine. Within the first few months of training, Leela Chess Zero had already reached the Grandmaster level, surpassing the strength of early releases of Rybka, Stockfish, and Komodo.
Leela continued to improve month by month using its machine-learning algorithm. In February 2019, Leela scored its first major tournament win when it defeated Houdini in the final of the second TCEC cup. Leela did not lose a game during the entire tournament.
Finally, Stockfish developers also continued to improve their program and in 2020 they came out with the latest chess bomb. In June 2020 an efficiently updatable neural network (NNUE) fork introduced by computer shogi programmers called Stockfish NNUE was discussed by developers. In July 2020 chess news reported that Stockfish NNUE had “broken new ground in computer chess by incorporating a neural network into the already incredibly powerful Stockfish chess engine.” An NNUE merge into Stockfish was then announced and development builds became available.
Nowadays Stockfish NNUE and Leela Chess Zero are dominating the computer chess tournaments and chess analysis tasks.
After that summary of chess engines history, we can introduce our NeoBook Project, because it was created using the previously mentioned chess technology advancements.
NeoBook is an online tool or web app designed to study chess openings interactively. Its acronym NEO stands for Neural Engine of Openings, as it was designed using the most recent trend in chess analysis: “Neural Networks” inspired by Google’s ambitious Alpha Zero project and other AI tools to give you the best studying experience.
This project stems from the dream of a chess master to create a tool that would make studying openings the best possible experience. With NeoBook we have made it easier, cheaper, more efficient, more understandable, more interactive, more modern, and it has the tremendous ability to improve every month with major updates, including the best chess analyses possible made by artificial intelligence nowadays. We have certainly achieved that dream!
The whole history of chess has brought us to this moment, the collaboration of humans and Artificial Intelligence at its finest, the beginning of a new era.
The main attraction of the book is the quality of the information that is offered to the users and the interactive way it is shown.