Title :
Using the particle swarm optimization technique to train a recurrent neural model
Author_Institution :
Rome Lab., NY, USA
Abstract :
We discuss the results of implementing an evolutionary learning technique entitled particle swarm optimization as described by Kennedy and Eberhart (1995). We present a number of results using this technique on a number of neural model architectures using the XOR problem and then conclude by applying it to a real problem-parsing natural language phrases
Keywords :
feedforward neural nets; genetic algorithms; grammars; learning (artificial intelligence); multilayer perceptrons; natural languages; neural net architecture; optimisation; recurrent neural nets; XOR problem; evolutionary learning technique; multilayered feedforward network; natural language phrase parsing; neural model architectures; particle swarm optimization technique; recurrent neural model training; Backpropagation algorithms; Convergence; Feeds; Laboratories; Natural languages; Particle swarm optimization;
Conference_Titel :
Tools with Artificial Intelligence, 1997. Proceedings., Ninth IEEE International Conference on
Conference_Location :
Newport Beach, CA
Print_ISBN :
0-8186-8203-5
DOI :
10.1109/TAI.1997.632235
