Title :
Novel Neural Network and Its Application in Hysteresis Modeling
Author :
An, Xiaoran ; Xu, Meng
Author_Institution :
Sch. of Electr. Eng. & Autom., Tianjin Polytech. Univ., Tianjin, China
Abstract :
A novel neural network with chaotic property is proposed. The network is composed by different neurons. Some activation function is chaotic iterative function instead of the conventional Sigmoid function. In the process of learning, taking advantage of the randomicity property and ergodicity property of chaos, the generalization capability and the optimizing efficiency can be improved. The simulation results prove the validity of the algorithm.
Keywords :
chaos; generalisation (artificial intelligence); hysteresis; iterative methods; learning (artificial intelligence); neural nets; optimisation; random processes; transfer functions; activation function; chaotic iterative function; chaotic property; conventional Sigmoid function; ergodicity property; generalization capability; hysteresis modeling; learning; neural network; optimizing efficiency; randomicity property; Artificial neural networks; Chaos; History; Hysteresis; Neurons; Noise; Training; chaos; hysteresis modeling; neural network;
Conference_Titel :
Modeling, Simulation and Visualization Methods (WMSVM), 2010 Second International Conference on
Conference_Location :
Sanya
Print_ISBN :
978-1-4244-7077-8
Electronic_ISBN :
978-1-4244-7078-5
DOI :
10.1109/WMSVM.2010.56
