Feedforward backpropagation artificial neural networks on reconfigurable meshes
| Autor: | John Jenq, Wing-Ning Li |
|---|---|
| Rok vydání: | 1998 |
| Předmět: |
Artificial neural network
Computer Networks and Communications business.industry Computer science Time delay neural network Computer Science::Neural and Evolutionary Computation Parallel algorithm Feed forward Image processing Backpropagation Hardware and Architecture Pattern recognition (psychology) Artificial intelligence business Software |
| Zdroj: | Future Generation Computer Systems. 14:313-319 |
| ISSN: | 0167-739X |
| DOI: | 10.1016/s0167-739x(98)00036-3 |
| Popis: | The artificial neural networks (ANNs) have been used successfully in applications such as pattern recognition, image processing, automation and control. Majority of today's applications use backpropagate feedforward ANN. In this paper, two methods of P pattern L layer ANN learning on n × n RMESH have been presented. One required memory space of O(nL) but conceptually is simpler to develop and the other uses pipelined approach which reduces the memory requirement to O(L). Both of these algorithms take O(PL) time and are optimal for RMESH architecture. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect