Sen, P. ; Chakrabarti, B. K. (1989) Available phase space and robustness of the layered feed-forward neural network Physical Review A, 40 (8). pp. 4700-4703. ISSN 1050-2947
Full text not available from this repository.
Official URL: http://pra.aps.org/abstract/PRA/v40/i8/p4700_1
Related URL: http://dx.doi.org/10.1103/PhysRevA.40.4700
Abstract
We have studied numerically the basin of attraction of learned patterns and the phase-space fraction available to them in a layered feed-forward model with iterated learning rule. We observe a new transition at α∓ 0.03, apart from the discontinuous one at α∓0.18 reported earlier for the model (α is the fraction of the number of learned patterns to the number of neurons in a layer). These two transitions are speculated to be identical to the corresponding transitions at α∓0.05 and α∓0.14 (discontinuous) in the Hopfield model, which occurs in the first few layers, and finally shift in position due to amplification (and filtration) effect of the layered systems. The robustness of such a layered network against the loss of neurons in some intermediate layers is also studied.
Item Type: | Article |
---|---|
Source: | Copyright of this article belongs to The American Physical Society. |
ID Code: | 44888 |
Deposited On: | 23 Jun 2011 09:52 |
Last Modified: | 23 Jun 2011 09:52 |
Repository Staff Only: item control page