Abstract | ||
---|---|---|
This paper studies a cascade system of dynamic binary neural networks. The system is characterized by signum activation function, ternary connection parameters, and integer threshold parameters. As a fundamental learning problem, we consider storage and stabilization of one desired binary periodic orbit that corresponds to control signals of switching circuits. For the storage, we present a simple method based on the correlation learning. For the stabilization, we present a sparsification method based on the mutation operation in the genetic algorithm. Using the Gray-code-based return map, the storage and stability can be investigated. Performing numerical experiments, effectiveness of the learning method is confirmed. |
Year | DOI | Venue |
---|---|---|
2015 | 10.1587/transinf.2014OPP0011 | IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS |
Keywords | Field | DocType |
binary neural networks, deep learning, switching circuits | Pattern recognition,Computer science,Binary neural network,Types of artificial neural networks,Artificial intelligence,Cascade,Deep learning,Artificial neural network,Periodic orbits | Journal |
Volume | Issue | ISSN |
E98D | 9 | 1745-1361 |
Citations | PageRank | References |
3 | 0.43 | 12 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jungo Moriyasu | 1 | 6 | 1.53 |
Toshimichi Saito | 2 | 382 | 74.54 |