Images, frames, and connectionist hierarchies
Images, frames, and connectionist hierarchies
复制标题
DOI：
10.1162/neco.2006.18.10.2293
复制
发表时间：
2006-10-01
影响因子：
2.9
通讯作者：
Dayan, Peter
中科院分区：
文献类型：
--
作者：
Dayan, Peter
The representation of hierarchically structured knowledge in systems using distributed patterns of activity is an abiding concern for the connectionist solution of cognitively rich problems. Here, we use statistical unsupervised learning to consider semantic aspects of structured knowledge representation. We meld unsupervised learning notions formulated for multilinear models with tensor product ideas for representing rich information. We apply the model to images of faces.
