Overview
The idea of this project is to build an Engine and Tablebase for a Cambridge-based smaller variant of the classic game. This project would be carried out in contact with Ross Smith from 5asideCHESS, an organisation focused on improving social connections. Offered to motivated students passionate about machine learning and chess.
FAQs
- What will I learn in this Project?
You will gain hands-on experience building neural networks and dynamic programming systems, building on classic approaches to a famous problem.
- What is the objective of the project?
Build a neural network based analysis engine for this smaller version of chess, following the state-of-the-art approaches used in solving chess and checkers. The smaller size of the game allows for similar approaches to be more powerful, especially when considering tablebases. Ideal project deliverables would be a 5aside engine and 5aside tablebase, combined into a system shown to be stronger than humans. Particularly interesting would be insights into the possible approaches in 5aside that are computationally infeasible for the full game.
- How does this fit into the bigger picture?
5asideCHESS was set up as a social enterprise in 2015 by co-founders Ross Smith and Ian McKay as they were concerned about the levels of disconnection and inequality that they saw in society. The project has a huge mission – to tackle loneliness, social isolation and the mental ill health and depression that these issues can cause. 5asideCHESS was invented as a shorter, quicker version of the traditional game of chess. You may have seen them and their chessboards around Cambridge, like at the market and the cafe downstairs.
