在线查找
与资料的链接
在图书馆查找
正在查找有这资料的图书馆...
详细书目
| 材料类型: | 互联网资源 |
|---|---|
| 文件类型: | 互联网资源 |
| 所有的著者/提供者: |
Michael I Jordan; Robert A Jacobs; MASSACHUSETTS INST OF TECH CAMBRIDGE ARTIFICIAL INTELLIGENCE LAB. |
| OCLC号码: | 227806326 |
| 注意: | Sponsored in part by the Defense Advanced Research Projects Angecy and National Science Foundation Grants ECS92-16531 and IRI90-13991. |
| 描述: | 31 p. |
摘要:
We present a tree-structured architecture for supervised learning. The statistical model underlying the architecture is a hierarchical mixture model in which both the mixture coefficients and the mixture components are generalized linear models (GLIM's). Learning is treated as a maximum likelihood problem; in particular, we present an Expectation-Maximization (EM) algorithm for adjusting the parameters of the architecture. We also develop an on-line learning algorithm in which the parameters are updated incrementally. Comparative simulation results are presented in the robot dynamics domain.
标签
添加标签 目的是为 "Hierarchical Mixtures of Experts and the EM Algorithm".
争取是第一个!
相似资料
相关主题:(22)
- Statistics and Probability.
- Cybernetics.
- Mathematical models.
- Algorithms.
- Learning.
- Hierarchies.
- Simulation.
- Neural nets.
- Dynamics.
- Parameters.
- Maximum likelihood estimation.
- Robots.
- Statistics.
- Coefficients.
- Least squares method.
- Artificial intelligence.
- Linear regression analysis.
- Applied mathematics.
- DIVIDE AND CONQUER ALGORITHMS
- EM(EXPECTATION MAXIMIZATION)
- SUPERVISED LEARNING
- DECISION TREES
