A Rigorous Verification of Chaos in A 3D Neural Network
- Resource Type
- Conference
- Authors
- Fangyan Yang; Ping Zhou; Qingdu Li
- Source
- 2006 International Conference on Communications, Circuits and Systems Communications, Circuits and Systems Proceedings, 2006 International Conference on. 3:2111-2113 Jun, 2006
- Subject
- Communication, Networking and Broadcast Technologies
Computing and Processing
Components, Circuits, Devices and Systems
Chaos
Neural networks
Neurons
Artificial neural networks
Mathematical model
Biological neural networks
Computer simulation
Nonlinear systems
Telecommunications
Biological processes
- Language
This paper proposes a rigorous verification of chaos in an artificial neural network (ANN) consisting of three neurons by virtue of the topological horseshoe theory. Because the two disjoint compact subsets producing a horseshoe we found in a certain cross-section both expand in one directions under the forth Poincaré return map, we conclude that there exists chaos in the ANN.