eCite Digital Repository

Generalising the discriminative restricted Boltzmann machines


Cherla, S and Tran, SN and d'Avila Garcez, A and Weyde, T, Generalising the discriminative restricted Boltzmann machines, Proceedings of the 26th International Conference on Artificial Neural Networks: Artificial Neural Networks and Machine Learning, Part II, 11-14 September 2017, Alghero, Italy, pp. 111-119. (2017) [Refereed Conference Paper]

Copyright Statement

Copyright 2017 Springer

DOI: doi:10.1007/978-3-319-68612-7_13


We present a novel theoretical result that generalises the Discriminative Restricted Boltzmann Machine (DRBM). While originally the DRBM was defined assuming the {0,1}-Bernoulli distribution in each of its hidden units, this result makes it possible to derive cost functions for variants of the DRBM that utilise other distributions, including some that are often encountered in the literature. This paper shows that this function can be extended to the Binomial and {−1,+1}-Bernoulli hidden units.

Item Details

Item Type:Refereed Conference Paper
Keywords:discriminative learning, hidden layer activation function, restricted Boltzmann machine
Research Division:Information and Computing Sciences
Research Group:Artificial intelligence
Research Field:Intelligent robotics
Objective Division:Culture and Society
Objective Group:Communication
Objective Field:Visual communication
UTAS Author:Tran, SN (Dr Son Tran)
ID Code:140701
Year Published:2017
Web of Science® Times Cited:7
Deposited By:Information and Communication Technology
Deposited On:2020-09-01
Last Modified:2020-11-09

Repository Staff Only: item control page