Speedup Learning

Speedup learning is a branch of machine learning that studies learning mechanisms for speeding up problem solvers based on problem solving experience. The input to a speedup learner typically consists of observations of prior problem-solving experience, which may include traces of the problem solver’s operations and/or solutions to solved problems. The output is knowledge that the problem solver can exploit to find solutions more quickly than before learning without seriously effecting solution quality. The most distinctive feature of speedup learning, compared to most branches of machine learning, is that the learned knowledge does not provide the problem solver with the ability to solve new problem instances. Rather, the learned knowledge is intended solely to facilitate faster solution times compared to the solver without the knowledge.