Neural models for part-whole hierarchies.
In: Mozer, MC and Jordan, MI and Petsche, T, (eds.)
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 9.
(pp. 17 - 23).
M I T PRESS
We present a connectionist method for representing images that explicitly addresses their hierarchical nature. It blends data from neuroscience about whole-object viewpoint sensitive cells in inferotemporal cortex(8) and attentional basis-field modulation in V4(3) 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.
|Title:||Neural models for part-whole hierarchies|
|Event:||10th Annual Conference on Neural Information Processing Systems (NIPS)|
|Dates:||1996-12-02 - 1996-12-05|
|UCL classification:||UCL > School of Life and Medical Sciences > Faculty of Life Sciences > Gatsby Computational Neuroscience Unit|
Archive Staff Only