A Computer Composes A Fabled Problem: Four Knights vs. Queen
This work addresses the problem of generating human-like creativity in computational systems for targeted problems with no clear solution path, representing an incremental advance in the field of computational creativity.
The authors tackled the challenge of automatically composing a rare and interesting chess problem, specifically a 'Four Knights vs. Queen' scenario, using the Chesthetica prototype with the Digital Synaptic Neural Substrate (DSNS) approach, achieving this in just 10 days on a small computer with low processing power and memory.
We explain how the prototype automatic chess problem composer, Chesthetica, successfully composed a rare and interesting chess problem using the new Digital Synaptic Neural Substrate (DSNS) computational creativity approach. This problem represents a greater challenge from a creative standpoint because the checkmate is not always clear and the method of winning even less so. Creating a decisive chess problem of this type without the aid of an omniscient 7-piece endgame tablebase (and one that also abides by several chess composition conventions) would therefore be a challenge for most human players and composers working on their own. The fact that a small computer with relatively low processing power and memory was sufficient to compose such a problem using the DSNS approach in just 10 days is therefore noteworthy. In this report we document the event and result in some detail. It lends additional credence to the DSNS as a viable new approach in the field of computational creativity. In particular, in areas where human-like creativity is required for targeted or specific problems with no clear path to the solution.