| DOI | Resolve DOI: https://doi.org/10.1109/IJCNN.2018.8489413 |
|---|
| Author | Search for: Li, Yifeng1; Search for: Zhu, Xiaodan |
|---|
| Affiliation | - National Research Council Canada. Digital Technologies
|
|---|
| Format | Text, Article |
|---|
| Conference | 2018 International Joint Conference on Neural Networks (IJCNN), July 7-13, 2018, Rio de Janeiro, Brazil |
|---|
| Subject | deep learning; generative model; exponential family; restricted Boltzmann machine; annealed importance sampling |
|---|
| Abstract | In this paper, we investigate restricted Boltzmann machines (RBMs) from the exponential family perspective, en-abling the visible units to follow any suitable distributions from the exponential family. We derive a unified view to compute the free energy function for exponential family RBMs (exp-RBMs). Based on that, annealed important sampling (AIS) is generalized to the entire exponential family, allowing for estimating the log-partition function and log-likelihood. Our experiments on a document processing task demonstrate that the generalized free energy functions and AIS estimation perform well in helping capture useful knowledge from the data; the estimated log-partition functions are stable. The appropriate instances of exp-RBMs can generate novel and meaningful samples and can be applied to classification tasks. |
|---|
| Publication date | 2018-10-15 |
|---|
| Publisher | IEEE |
|---|
| 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 | 3cf762e2-b2b8-4072-b7b0-fe6c993f8c9f |
|---|
| Record created | 2019-04-12 |
|---|
| Record modified | 2020-03-16 |
|---|
