A VLSI architecture for weight perturbation on chip learning implementation

In this paper we present the analog on-chip learning architecture of a gradient descent learning algorithm: the weight perturbation learning algorithm. From the circuit implementation point of view our approach is based on current mode and translinear operated circuits. The proposed architecture is very efficient in terms of speed, size, precision and power consumption; moreover it exhibits also high scalability and modularity.

[1]  A.H.M. van Roermund,et al.  A reduced-area low-power low-voltage single-ended differential pair , 1997 .

[2]  Marwan A. Jabri,et al.  Weight perturbation: an optimal architecture and learning technique for analog VLSI feedforward and recurrent multilayer networks , 1992, IEEE Trans. Neural Networks.

[3]  Ronald S. Gyurcsik,et al.  Toward a general-purpose analog VLSI neural network with on-chip learning , 1997, IEEE Trans. Neural Networks.

[4]  Daniele D. Caviglia,et al.  An experimental analog VLSI neural network with on-chip back-propagation learning , 1992, ESSCIRC '92: Eighteenth European Solid-State Circuits conference.

[5]  Daniele D. Caviglia,et al.  An analog on-chip learning circuit architecture of the weight perturbation algorithm , 2000, 2000 IEEE International Symposium on Circuits and Systems. Emerging Technologies for the 21st Century. Proceedings (IEEE Cat No.00CH36353).

[6]  Andrzej Cichocki,et al.  Neural networks for optimization and signal processing , 1993 .

[7]  Daniele D. Caviglia,et al.  Analog CMOS current mode neural primitives , 2000, 2000 IEEE International Symposium on Circuits and Systems. Emerging Technologies for the 21st Century. Proceedings (IEEE Cat No.00CH36353).

[8]  Joshua Alspector,et al.  A Study of Parallel Perturbative Gradient Descent , 1994, NIPS.

[9]  Christofer Toumazou,et al.  Analogue IC design : the current-mode approach , 1993 .

[10]  Francois Krummenacher,et al.  A 4-MHz CMOS Continuous-Time Filter with On-Chip Automatic Tuning , 1987, ESSCIRC '87: 13th European Solid-State Circuits Conference.