Slightly Beyond Turing's Computability for Studying Genetic Programming

Inspired by genetic programming (GP), we study iterative algorithms for non-computable tasks and compare them to naive models. This framework justifies many practical standard tricks from GP and also provides complexity lower-bounds which justify the computational cost of GP thanks to the use of Kolmogorov’s complexity in bounded time.

• Type: Conference
• Year: 2007
• Where: MCU
• Authors: Olivier Teytaud
• Keywords: GP Thanks, Hardware, Kolmogorov’s Complexity, MCU 2007, Practical Standard Tricks