English

Mixed integer programming formulation of unsupervised learning

Machine Learning 2020-01-22 v1 Disordered Systems and Neural Networks Machine Learning

Abstract

A novel formulation and training procedure for full Boltzmann machines in terms of a mixed binary quadratic feasibility problem is given. As a proof of concept, the theory is analytically and numerically tested on XOR patterns.

Keywords

Cite

@article{arxiv.2001.07278,
  title  = {Mixed integer programming formulation of unsupervised learning},
  author = {Arturo Berrones-Santos},
  journal= {arXiv preprint arXiv:2001.07278},
  year   = {2020}
}