Name
Abstract | ||
|---|---|---|
In this paper we develop a class of nonlinear generative models for high-dimensional time series. We first propose a model based on the restricted Boltzmann machine (RBM) that uses an undirected model with binary latent variables and real-valued "visible" variables. The latent and visible variables at each time step receive directed connections from the visible variables at the last few time-steps. This "conditional" RBM (CRBM) makes on-line inference efficient and allows us to use a simple approximate learning procedure. We demonstrate the power of our approach by synthesizing various sequences from a model trained on motion capture data and by performing on-line filling in of data lost during capture. We extend the CRBM in a way that preserves its most important computational properties and introduces multiplicative three-way interactions that allow the effective interaction weight between two variables to be modulated by the dynamic state of a third variable. We introduce a factoring of the implied three-way weight tensor to permit a more compact parameterization. The resulting model can capture diverse styles of motion with a single set of parameters, and the three-way interactions greatly improve its ability to blend motion styles or to transition smoothly among them. Videos and source code can be found at http://www.cs.nyu.edu/~gwtaylor/publications/jmlr2011. |
Year | DOI | Venue |
|---|---|---|
2011 | 10.5555/1953048.2021035 | Journal of Machine Learning Research |
Keywords | Field | DocType |
distributed-state models,implied three-way weight tensor,undirected model,three-way interaction,nonlinear generative model,motion style,generating high-dimensional time series,motion capture data,binary latent variable,multiplicative three-way interaction,resulting model,visible variable | Motion capture,Restricted Boltzmann machine,Nonlinear system,Multiplicative function,Inference,Computer science,Source code,Latent variable,Artificial intelligence,Machine learning,Binary number | Journal |
Volume | ISSN | Citations |
12, | 1532-4435 | 42 |
PageRank | References | Authors |
1.86 | 57 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Graham W. Taylor | 1 | 1523 | 127.22 |
| geoffrey e hinton | 2 | 40435 | 4751.69 |
| Sam T. Roweis | 3 | 4556 | 497.42 |