Gigamachine: incremental machine learning on desktop computers
Abstract
We present a concrete design for Solomonoff's incremental machine learning system suitable for desktop computers. We use R5RS Scheme and its standard library with a few omissions as the reference machine. We introduce a Levin Search variant based on a stochastic Context Free Grammar together with new update algorithms that use the same grammar as a guiding probability distribution for incremental machine learning. The updates include adjusting production probabilities, re-using previous solutions, learning programming idioms and discovery of frequent subprograms. The issues of extending the a priori probability distribution and bootstrapping are discussed. We have implemented a good portion of the proposed algorithms. Experiments with toy problems show that the update algorithms work as expected.
Cite
@article{arxiv.1709.03413,
title = {Gigamachine: incremental machine learning on desktop computers},
author = {Eray Özkural},
journal= {arXiv preprint arXiv:1709.03413},
year = {2017}
}
Comments
This is the original submission for my AGI-2010 paper titled Stochastic Grammar Based Incremental Machine Learning Using Scheme which may be found on http://agi-conf.org/2010/wp-content/uploads/2009/06/paper_24.pdf and presented a partial but general solution to the transfer learning problem in AI. arXiv admin note: substantial text overlap with arXiv:1103.1003