Images, Frames, and Connectionist Hierarchies
- 1 October 2006
- journal article
- research article
- Published by MIT Press in Neural Computation
- Vol. 18 (10) , 2293-2319
- https://doi.org/10.1162/neco.2006.18.10.2293
Abstract
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.Keywords
This publication has 37 references indexed in Scilit:
- Learning distributed representations of concepts using linear relational embeddingIEEE Transactions on Knowledge and Data Engineering, 2001
- Linear object classes and image synthesis from a single example imagePublished by Institute of Electrical and Electronics Engineers (IEEE) ,1997
- Spatial Transformations in the Parietal Cortex Using Basis FunctionsJournal of Cognitive Neuroscience, 1997
- Modeling the manifolds of images of handwritten digitsIEEE Transactions on Neural Networks, 1997
- Image Representations for Visual LearningScience, 1996
- Using generative models for handwritten digit recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1996
- A theory of visual stability across saccadic eye movementsBehavioral and Brain Sciences, 1994
- Labelling Recursive Auto-associative MemoryConnection Science, 1994
- Eigenfaces for RecognitionJournal of Cognitive Neuroscience, 1991
- Pattern recognition by labeled graph matchingNeural Networks, 1988