Research Abstract


Chaotic Boltzmann machines

2013年4月5日 Scientific Reports 3 : 1610 doi: 10.1038/srep01610


鈴木 秀幸1, 井村 順一2, 堀尾 喜彦3 & 合原 一幸1

  1. 東京大学 生産技術研究所 最先端数理モデル連携研究センター
  2. 東京工業大学 大学院情報理工学研究科
  3. 東京電機大学 大学院先端科学技術研究科
The chaotic Boltzmann machine proposed in this paper is a chaotic pseudo-billiard system that works as a Boltzmann machine. Chaotic Boltzmann machines are shown numerically to have computing abilities comparable to conventional (stochastic) Boltzmann machines. Since no randomness is required, efficient hardware implementation is expected. Moreover, the ferromagnetic phase transition of the Ising model is shown to be characterised by the largest Lyapunov exponent of the proposed system. In general, a method to relate probabilistic models to nonlinear dynamics by derandomising Gibbs sampling is presented.