CAS Key Laboratory of Theoretical Physics

Institute of Theoretical Physics

Chinese Academy of Sciences

Seminar

Title

题目

Riemann-Theta Boltzmann Machine

Speaker

报告人

Affiliation

所在单位

Date

日期

Venue

地点

Abstract

摘要

A general Boltzmann machine with continuous visible and discrete integer valued hidden states is introduced. Under mild assumptions about the connection matrices, the probability density function of the visible units can be solved for analytically, yielding a novel parametric density function involving a ratio of Riemann-Theta functions. The conditional expectation of a hidden state for given visible states can also be calculated analytically, yielding a derivative of the logarithmic Riemann-Theta function. The conditional expectation can be used as activation function in a feedforward neural network, thereby increasing the modelling capacity of the network. Both the Boltzmann machine and the derived feedforward neural network can be successfully trained via standard gradient- and non-gradient-based optimization techniques.

Contact Person

所内联系人