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

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.




References:
[1] Georges.G.E. Gielen and Rob.A. Rutenbar. Computer-Aided Design of
Analog and Mixed-Signal Integrated Circuits. Proceedings of the IEEE,
Vol.88:pp.1825-1852, December 2000.
[2] T. McConaghy and G. Gielen. Automation in Mixed-Signal Design:
Challenges and Solutions in the Wake of the Nano Era. In Proc. of
ICCAD, pages 461-463, November 2006.
[3] Rob.A. Rutenbar, Georges.G.E. Gielen, and J.Roychowdhury. Hierarchical
Modeling, Optimization, and Synthesis for System-Level Analog
and RF Designs. Proceedings of the IEEE, Vol.95:pp.640-669, March
2007.
[4] W. Daems, G. Gielen, and W. Sansen. Simulation-Based Generation of
Posynomial Performance Models for the Sizing of Analog Integrated
Circuits. IEEE Trans. CADICS, Vol.22:pp.517-534, May 2003.
[5] M. Avci and T. Yildirim. Neural Network Based MOS Transistor
Geometry Decision for TSMC 0.18 Process Technology. In Proc. of
ICCS, pages 615-622, 2006.
[6] F. Gunes, F. Gurgen, and G. Torpi, H. Signal-noise neural network
model for active microwave devices. IEE Proceedings Circuits Devices
and Systems, Vol.143:pp.1-8, 1996.
[7] N. Kahraman and T. Yildirim. Technology Independent Circuit Sizing
for Fundamental Analog Circuits using Artificial Neural Networks. In
Proc. of PRIME, pages 1-4, 2008.
[8] N. Kahraman and T. Yildirim. Technology independent circuit sizing
for standard cell based design using neural network. Digital Signal
Processing, Vol.19:pp.708-714, 2009.
[9] F. Djeffala, M. Chahdib, A. Benhayaa, and M.L. Hafianea. An approach
based on neural computation to simulate the nanoscale CMOS circuit.
Solid State Electronics, Vol.51:pp.48-56, 2007.
[10] S.K. Mandal, S. Sural, and A. Patra. ANN-and PSO-Based Synthesis
of On-Chip Spiral Inductors for RF ICs. IEEE Transaction CADICS,
Vol.27:pp.188-192, January 2008.
[11] G.H. John and P. Langley. Static Versus Dynamic Sampling for Data
Mining. In Proc. of Knowledge Discovery and Data Mining, 1996.
[12] F. Provost, D. Jensen, and T. Oates. Efficient Progressive Sampling. In
Proc. of Knowledge Discovery and Data Mining, pages 23-32, 1999.
[13] C. Meek, B. Thiesson, and D. Heckerman. The Learning-Curve Sampling
Method Applied to Model-Based Clustering. Journal of Machine
Learning Research, Vol.2:pp.397-418, February 2002.
[14] A. Satyanarayana and I. Davidson. A Dynamic Adaptive Sampling
Algorithm for Real World Applications: Finger Print Recognition and
Face Recognition. In Proc. of ISMIS, pages 631-640, 2005.
[15] V.K. Devabhaktuni and Q.J. Zhang. Neural Network Training-Driven
Adaptive Sampling Algorithm for Microwave Modeling. In Proc. of
European Microwave Conference, 2000.
[16] G. Wolfe and R. Vemuri. Adaptive Sampling and Modeling of Analog
Circuit Performance Parameters with Pseudo-Cubic Splines. In Proc. of
ICCAD, pages 931-836, 2004.
[17] D. Dhabak and S. Pandit. Performance Modeling of Nano-scale CMOS
Inverter using Artificial Neural Network. In Proc. of IESPC, pages 33-
36, 2011.
[18] Q.J. Zhang, K.C. Gupta, and V.K. Devabhaktuni. Artificial Neural
Networks for RF and Microwave Design: From Theory to Practice. IEEE
Trans. MTT, Vol.51:1339-1350, April 2003.
[19] W. Zhao and Y. Cao. New Generation of Predictive Technology Model
for Sub-45 nm Early Design Exploration. IEEE Transactions Electron
Devices, Vol.53:pp.2816-2823, November 2006.
[20] L. Kuipers and H. Niederreiter. Uniform distribution of sequences. Dover
Publications.
[21] I. C. Yeh. Modeling of Strength of High-Performance Concrete
using Artificial Neural Network. Cement and Concrete Research,
Vol.28:pp.1797-1808, 1998.
[22] http://archive.ics.uci.edu/ml/datasets/Concrete+Compressive+Strength.