| P. Dayan. Recurrent sampling models for the Helmholtz machine. Neur. Comp., 11:653-77, 2000. |
.... area V1, for example, they may be responsible for surround e ects and for the non linear response properties of simple and complex cells [11] This view is supported by connectionist neuron learning paradigms in which lateral connections statistically de correlate [10] or nd correlation structure [1] within the activities of cells in an area. Both paradigms are in accordance with the notion that the lateral connections form an attractor network. The activation patterns which form its attractors correlate nearby cell s activations but de correlate distant cell s activations. The attractor ....
P. Dayan. Recurrent sampling models for the Helmholtz machine. Neur. Comp., 11:653-77, 2000.
No context found.
Dayan, P (1999). Recurrent sampling models for the Helmholtz machine. Neural Computation, 11:653-677.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC