Abstract
There is little consensus about the computational function of top-down synaptic connections in the visual system. Here we explore the hypothesis that top-down connections, like bottom-up connections, reflect part whole relationships. We analyze a recurrent network with bidirectional synaptic interactions between a layer of neurons representing parts and a layer of neurons representing wholes. Within each layer, there is lateral inhibition. When the network detects a whole, it can rigorously enforce part-whole relationships by ignoring parts that do not belong. The network can complete the whole by filling in missing parts. The network can refuse to recognize a whole, if the activated parts do not conform to a stored part-whole relationship. Parameter regimes in which these behaviors happen are identified using the theory of permitted and forbidden sets [3, 4]. The network behaviors are illustrated by recreating Rumelhart and McClelland's "interactive activation" model [7].
Original language | English (US) |
---|---|
Title of host publication | Advances in Neural Information Processing Systems 18 - Proceedings of the 2005 Conference |
Pages | 563-570 |
Number of pages | 8 |
State | Published - Dec 1 2005 |
Externally published | Yes |
Event | 2005 Annual Conference on Neural Information Processing Systems, NIPS 2005 - Vancouver, BC, Canada Duration: Dec 5 2005 → Dec 8 2005 |
Other
Other | 2005 Annual Conference on Neural Information Processing Systems, NIPS 2005 |
---|---|
Country/Territory | Canada |
City | Vancouver, BC |
Period | 12/5/05 → 12/8/05 |
All Science Journal Classification (ASJC) codes
- Computer Networks and Communications
- Information Systems
- Signal Processing