Abstract
In this paper, we propose the majority algorithm to choose the connection weights for the neural networks with quantized connection weights of ±1 and 0. \Ve also obtained the layered network to solve the parity problem with the input of arbitrary number N through an application of this algorithm. The network can be expected to have the same ability of generalization as the network trained with learning rules. This is because it is possible to decide the connection weights, regardless of the size of the training set. One can decide connection weights without learning according to our case study. Thus, we expect that the proposed algorithm may be applied for a realtime processing.
Original language | English |
---|---|
Pages (from-to) | 1059-1064 |
Number of pages | 6 |
Journal | IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences |
Volume | E83-A |
Issue number | 6 |
Publication status | Published - 2000 |
Externally published | Yes |
Keywords
- Limit cycles
- Multi-layer
- Neural networks
- Parity problem
- Quantized interconnection
ASJC Scopus subject areas
- Signal Processing
- Computer Graphics and Computer-Aided Design
- Electrical and Electronic Engineering
- Applied Mathematics