Please use this identifier to cite or link to this item:
https://doi.org/10.1016/S0925-2312(97)00030-1
Title: | On the solution of the parity problem by a single hidden layer feedforward neural network | Authors: | Setiono, R. | Keywords: | Feedforward network Parity problem Sigmoid function |
Issue Date: | 1-Sep-1997 | Citation: | Setiono, R. (1997-09-01). On the solution of the parity problem by a single hidden layer feedforward neural network. Neurocomputing 16 (3) : 225-235. ScholarBank@NUS Repository. https://doi.org/10.1016/S0925-2312(97)00030-1 | Abstract: | It is known that the N-bit parity problem is solvable by a standard feedforward neural network having a single hidden layer consisting of (N/2) + 1 hidden units if N is even and (N + 1)/2 hidden units if N is odd. The network does not allow a direct connection between the input layer and the output layer and the transfer function used in all hidden units and the output unit is the usual sigmoidal function σ(x)-1/(1 + exp(-x)). We show that such a solution can be easily obtained by solving a system of linear equations. | Source Title: | Neurocomputing | URI: | http://scholarbank.nus.edu.sg/handle/10635/99365 | ISSN: | 09252312 | DOI: | 10.1016/S0925-2312(97)00030-1 |
Appears in Collections: | Staff Publications |
Show full item record
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.