Title :
Speed-up of learning in second order neural networks and its application to model synthesis of electrical devices
Author :
Wilk, E. ; Wilk, E. ; Morgenstern, B.
Author_Institution :
Univ. of the Federal Armed Forces, Hamburg, Germany
Abstract :
We use neural networks to approximate the terminal behaviour of electrical devices, maintaining the parameter dependencies. To accelerate the approximation time, we have improved the adaption rule by an adaptive evaluation of the learning parameters on the base of second-order sigma-pi neurons. The network paradigm is then automatically transformed either into a netlist of an electrical subcircuit (for example, SPICE-simulation) or into a mathematical description language (for example, a behavioural simulator like SABER). Examples demonstrate the very accurate representation of nonlinear electrical devices for circuit simulation
Keywords :
analogue circuits; analogue-digital conversion; backpropagation; circuit analysis computing; feedforward neural nets; function approximation; logic gates; A/D converter; SPICE-simulation; analog circuit simulation; backpropagation; electrical devices; feedforward neural network; learning parameters; macromodel; model synthesis; second order neural networks; second-order sigma-pi neurons; Analog circuits; Backpropagation; Circuit simulation; Feedforward neural networks; Intelligent networks; Multi-layer neural network; Network synthesis; Neural networks; Neurons; Voltage;
Conference_Titel :
Neural Networks, 1996., IEEE International Conference on
Conference_Location :
Washington, DC
Print_ISBN :
0-7803-3210-5
DOI :
10.1109/ICNN.1996.549032
