Thu 1/20/94, WeH 4601, 1:30pm. --------------------------------------------------- The Evolution of Mental Models Astro Teller --------------------------------------------------- Most interesting problems do not have solutions that are simple mappings from the inputs to the correct outputs; some kind of internal state or memory is needed to operate well or optimally in these domains. Traditionally, genetic programming(GP) has concentrated on solving problems in the functional/reactive arena. This has been largely due to the absence of a natural way to incorporate memory into the paradigm. Indexed Memory fills this gap. It is a seamless addition to the GP paradigm that allows the evolution of effective gathering, storage, and retrieval of arbitrarily complicated state information. This addition opens up the field of GP to the entire space of algorithms and this in turn presents new challenges for fields in evolutionary computation. ======================================================================== I. A short introduction to Genetic Programming II. Indexed Memory: a simple, effective addition to the GP paradigm III. Tartarus: a test environment for evolving mental models (Video) IV. The algorithmic completeness of GP with Indexed Memory V. Challenges in evolving algorithms ========================================================================