Title :
An inverse-deviation threshold approach in neural network controllers
Author :
Bo, Li ; Yuhui, Li ; Tiangui, Zhang
Author_Institution :
Dept. of Comput. Sci., Kunming Univ. of Sci. & Technol., China
Abstract :
An approach of inverse-deviation threshold is presented. The approach introduces an inverse-deviation function into the output neuron threshold in neural network controllers. The threshold can be dynamically changed by inverse-deviation function to adjust time-and-space accumulation effect of signals in neural network and improve neural network learning condition. This approach is advantageous to high speed response of neural network control systems
Keywords :
learning (artificial intelligence); neurocontrollers; high speed response; inverse-deviation function; inverse-deviation threshold approach; neural network control systems; neural network controllers; neural network learning condition; output neuron threshold; time-and-space accumulation effect; Chemicals; Control systems; Error correction; Feedforward neural networks; Intelligent networks; Natural gas; Neural networks; Neurons; Nonlinear control systems; Stability;
Conference_Titel :
Intelligent Processing Systems, 1997. ICIPS '97. 1997 IEEE International Conference on
Conference_Location :
Beijing
Print_ISBN :
0-7803-4253-4
DOI :
10.1109/ICIPS.1997.672811
