eCite Digital Repository
Generalising the discriminative restricted Boltzmann machines
Citation
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
Abstract
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 |
| Downloads: | 0 |
Repository Staff Only: item control page