ARTIFICIAL NEURAL NETWORKS AS AIDS IN-CIRCUIT DESIGN

This paper introduces the application of software implementations of artificial neural networks in the design of microelectronic circuits. The device dimensions of CMOS transistors can be easily obtained from trained artificial neural networks. Data generated by circuit simulation programs such as SPICE or calculations using circuit formulae such as those presented in this paper can be used to train the artificial neural networks. An example of the design of an operational transconductance amplifier using this method is presented. Supervised learning in multilayer feedforward neural networks using the so-called back-propagation algorithm is used to demonstrate the method.