| DOI | Resolve DOI: https://doi.org/10.1007/978-3-030-30487-4_22 |
|---|
| Author | Search for: Li, Yifeng1ORCID identifier: https://orcid.org/0000-0002-4873-6928; Search for: Zhu, XiaodanORCID identifier: https://orcid.org/0000-0003-3856-3696 |
|---|
| Affiliation | - National Research Council of Canada. Digital Technologies
|
|---|
| Format | Text, Article |
|---|
| Conference | 28th International Conference on Artificial Neural Networks, ICANN 2019, September 17-19, 2019, Munich, Germany |
|---|
| Subject | capsule; restricted; Boltzmann machine; Helmholtz machine; deep generative model |
|---|
| Abstract | 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. |
|---|
| Publication date | 2019-09-09 |
|---|
| Publisher | Springer |
|---|
| In | |
|---|
| Series | |
|---|
| Language | English |
|---|
| Peer reviewed | Yes |
|---|
| Export citation | Export as RIS |
|---|
| Report a correction | Report a correction (opens in a new tab) |
|---|
| Record identifier | 64873d48-bac4-4d60-84b7-de040865b0e2 |
|---|
| Record created | 2021-02-04 |
|---|
| Record modified | 2021-02-04 |
|---|
