Commenced in January 2007
Frequency: Monthly
Edition: International
Paper Count: 1

Publications

1 Adaptive Sampling Algorithm for ANN-based Performance Modeling of Nano-scale CMOS Inverter

Authors: Dipankar Dhabak, Soumya Pandit

Abstract:

This paper presents an adaptive technique for generation of data required for construction of artificial neural network-based performance model of nano-scale CMOS inverter circuit. The training data are generated from the samples through SPICE simulation. The proposed algorithm has been compared to standard progressive sampling algorithms like arithmetic sampling and geometric sampling. The advantages of the present approach over the others have been demonstrated. The ANN predicted results have been compared with actual SPICE results. A very good accuracy has been obtained.

Keywords: adaptive sampling, CMOS Inverter, Nano-scale, ArtificialNeural Network

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1276