A probabilistic framework for nonlinearities in stochastic neural networks

Qinliang Su, Xuejun Liao, Lawrence Carin

Research output: Chapter in Book/Report/Conference proceedingConference contribution

6 Scopus citations

Abstract

We present a probabilistic framework for nonlinearities, based on doubly truncated Gaussian distributions. By setting the truncation points appropriately, we are able to generate various types of nonlinearities within a unified framework, including sigmoid, tanh and ReLU, the most commonly used nonlinearities in neural networks. The framework readily integrates into existing stochastic neural networks (with hidden units characterized as random variables), allowing one for the first time to learn the nonlinearities alongside model weights in these networks. Extensive experiments demonstrate the performance improvements brought about by the proposed framework when integrated with the restricted Boltzmann machine (RBM), temporal RBM and the truncated Gaussian graphical model (TGGM).
Original languageEnglish (US)
Title of host publicationAdvances in Neural Information Processing Systems
PublisherNeural information processing systems foundation
Pages4487-4496
Number of pages10
StatePublished - Jan 1 2017
Externally publishedYes

Bibliographical note

Generated from Scopus record by KAUST IRTS on 2021-02-09

Fingerprint

Dive into the research topics of 'A probabilistic framework for nonlinearities in stochastic neural networks'. Together they form a unique fingerprint.

Cite this