Neural Models for Part-Whole Hierarchies

We present a connectionist method for representing images that explicitlyaddresses their hierarchicalnature. It blends data fromneuroscience about whole-object viewpoint sensitive cells in inferotemporal cortex8 and attentional basis- eld modulation in V43 with ideas about hierarchical descriptions based on microfeatures.5,11 The resulting model makes critical use of bottom-up and top-down pathways for analysis and synthesis.6 We illustrate the model with a simple example of representing information about faces. 1 Hierarchical Models Images of objects constitute an important paradigm case of a representational hierarchy, in which `wholes', such as faces, consist of `parts', such as eyes, noses and mouths. The representation and manipulation of part-whole hierarchical information in xed hardware is a heavy millstone around connectionist necks, and has consequently been the inspiration for many interesting proposals, such as Pollack's RAAM.11 We turned to the primate visu...

• Type: Conference
• Year: 1996
• Where: NIPS
• Authors: Maximilian Riesenhuber, Peter Dayan
• Keywords: Face Units, Hierarchical, Mouth Units, NIPS 1996, NIPS 2007