File(s) under permanent embargo
Generalising the discriminative restricted Boltzmann machines
conference contribution
posted on 2023-05-23, 14:44 authored by Cherla, S, Son TranSon Tran, d'Avila Garcez, A, Weyde, TWe 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.
History
Publication title
Proceedings of the 26th International Conference on Artificial Neural Networks: Artificial Neural Networks and Machine Learning, Part IIVolume
10614Pagination
111-119Department/School
School of Information and Communication TechnologyPublisher
SpringerPlace of publication
SwitzerlandEvent title
26th International Conference on Artificial Neural Networks: Artificial Neural Networks and Machine LearningEvent Venue
Alghero, ItalyDate of Event (Start Date)
2017-09-11Date of Event (End Date)
2017-09-14Rights statement
Copyright 2017 SpringerRepository Status
- Restricted