COMPETITION AND MULTIPLE CAUSE MODELS
COMPETITION AND MULTIPLE CAUSE MODELS
复制标题
DOI：
10.1162/neco.1995.7.3.565
复制
发表时间：
1995-05-01
影响因子：
2.9
通讯作者：
ZEMEL, RS
中科院分区：
文献类型：
--
作者：
DAYAN, P;ZEMEL, RS
如果不同的原因可以在任何情况下相互作用以生成一组模式，那么对生成进行建模的系统也必须对相互作用进行建模。我们讨论了一种结合多种原因的方法，该方法基于Keeler等人（1991）的集成分割和识别架构。它比混合专家体系结构中的一种模式更具有合作性，而Saund（1994 a，B）最近提出的噪声或组合函数更具有竞争性。仿真验证了其有效性。
If different causes can interact on any occasion to generate a set of patterns, then systems modeling the generation have to model the interaction too. We discuss a way of combining multiple causes that is based on the Integrated Segmentation and Recognition architecture of Keeler et al. (1991). It is more cooperative than the-scheme embodied in the mixture of experts architecture, which insists that just one cause generate each output, and more competitive than the noisy-or combination function, which was recently suggested by Saund (1994a,b). Simulations confirm its efficacy.