Abstract | ||
---|---|---|
This paper studies a cascade system of two simple dynamic binary neural networks characterized by signum activation function and ternary connection parameters. In order to store a desired binary periodic orbit, we present a simple method based on the correlation learning. In order to sparsify the network connection, we present a simple method based on the genetic algorithm. The sparsification can be effective to reinforce stability of the stored periodic orbit. |
Year | DOI | Venue |
---|---|---|
2014 | 10.1007/978-3-319-12637-1_29 | Lecture Notes in Computer Science |
Keywords | Field | DocType |
Digital dynamical systems,stability,power electronics | Activation function,Computer science,Binary neural network,Algorithm,Ternary operation,Cascade,Artificial intelligence,Power electronics,Network connection,Genetic algorithm,Machine learning,Binary number | Conference |
Volume | ISSN | Citations |
8834 | 0302-9743 | 0 |
PageRank | References | Authors |
0.34 | 10 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jungo Moriyasu | 1 | 6 | 1.53 |
Toshimichi Saito | 2 | 31 | 4.85 |