| DOI | Trouver le DOI : https://doi.org/10.1007/978-3-030-30487-4_22 |
|---|
| Auteur | Rechercher : Li, Yifeng1Identifiant ORCID : https://orcid.org/0000-0002-4873-6928; Rechercher : Zhu, XiaodanIdentifiant ORCID : https://orcid.org/0000-0003-3856-3696 |
|---|
| Affiliation | - Conseil national de recherches Canada. Technologies numériques
|
|---|
| Format | Texte, Article |
|---|
| Conférence | 28th International Conference on Artificial Neural Networks, ICANN 2019, September 17-19, 2019, Munich, Germany |
|---|
| Sujet | capsule; restricted; Boltzmann machine; Helmholtz machine; deep generative model |
|---|
| Résumé | Neuroscience studies inspire that structures are needed in the hidden space of deep learning models. In this paper, we propose a capsule restricted Boltzmann machine and a capsule Helmholtz machine by replacing individual hidden variables with encapsulated groups of hidden variables. Our preliminary experiments show that capsule activities in both models can be dynamically determined in context, and these activity spectra exhibit between-class patterns and within-class variations. Our models offer a novel approach to visualizing and understanding the hidden states. |
|---|
| Date de publication | 2019-09-09 |
|---|
| Maison d’édition | Springer |
|---|
| Dans | |
|---|
| Série | |
|---|
| Langue | anglais |
|---|
| Publications évaluées par des pairs | Oui |
|---|
| Exporter la notice | Exporter en format RIS |
|---|
| Signaler une correction | Signaler une correction (s'ouvre dans un nouvel onglet) |
|---|
| Identificateur de l’enregistrement | 64873d48-bac4-4d60-84b7-de040865b0e2 |
|---|
| Enregistrement créé | 2021-02-04 |
|---|
| Enregistrement modifié | 2021-02-04 |
|---|
