VLSI Implementation of a Neural Model Using Spikes

The paper presents a VLSI approach to approximate thereal-time dynamics of a neuron model inspired from the classicalmodel of Hodgkin and Huxley, in which analog inputs and outputsare represented by short spikes. Both the transient and the steady-statebehaviours of these circuits depend only on process-independentlocal ratios, thus enabling single or multiple-chip VLSI implementationsof very large analog neural networks in which parallelism, asynchronyand temporal interactions are kept as important neural processingfeatures. Measurements on an integrated CMOS prototype confirmexperimentally the expected electrical and temporal behavioursof the proposed neural circuits and illustrate some outstandingfunctional features of the neural model: spike-mediated modulationof the neural activity, self-regulation of the total activityin neural groups, and emulation of temporal interaction mechanismswith well controlled time constants at different scales.

[1]  D. A. Fay,et al.  Real-time early vision neurocomputing , 1991, IJCNN-91-Seattle International Joint Conference on Neural Networks.

[2]  John Wawrzynek,et al.  Silicon Auditory Processors as Computer Peripherals , 1992, NIPS.

[3]  X. Arreguit,et al.  Analog CMOS photosensitive array for solar illumination monitoring , 1996, 1996 IEEE International Solid-State Circuits Conference. Digest of TEchnical Papers, ISSCC.

[4]  J.-P. Bardyn,et al.  A battery operated optical spot intensity measurement system , 1995, Proceedings ISSCC '95 - International Solid-State Circuits Conference.

[5]  Eric A. Vittoz,et al.  A communication scheme for analog VLSI perceptive systems , 1995 .

[6]  Stephen Grossberg,et al.  Nonlinear neural networks: Principles, mechanisms, and architectures , 1988, Neural Networks.

[7]  Christof Koch,et al.  Analog VLSI circuits for visual motion-based adaptation of post-saccadic drift , 1996, Proceedings of Fifth International Conference on Microelectronics for Neural Networks.

[8]  Richard F. Lyon,et al.  Improved implementation of the silicon cochlea , 1992 .

[9]  Eric A. Vittoz,et al.  A communication architecture tailored for analog VLSI artificial neural networks: intrinsic performance and limitations , 1994, IEEE Trans. Neural Networks.

[10]  Carver A. Mead,et al.  VLSI implementation of neural networks , 1990 .

[11]  Kwabena Boahen,et al.  A 48,000 pixel, 590,000 transistor silicon retina in current-mode subthreshold CMOS , 1994, Proceedings of 1994 37th Midwest Symposium on Circuits and Systems.

[12]  André van Schaik,et al.  Improved Silicon Cochlea using Compatible Lateral Bipolar Transistors , 1995, NIPS.

[13]  A. Hodgkin,et al.  A quantitative description of membrane current and its application to conduction and excitation in nerve , 1952, The Journal of physiology.

[14]  T. Delbruck.  Silicon retina with correlation-based, velocity-tuned pixels , 1993 .

[15]  F. J. Fernández,et al.  A VLSI Approach to the Implementation of Additive and Shunting Neural Networks , 1995, IWANN.

[16]  Kwabena Boahen.  Retinomorphic vision systems , 1996, Proceedings of Fifth International Conference on Microelectronics for Neural Networks.

[17]  Richard F. Lyon,et al.  An analog electronic cochlea , 1988, IEEE Trans. Acoust. Speech Signal Process..

[18]  Tobi Delbrück,et al.  Silicon retina with correlation-based, velocity-tuned pixels , 1993, IEEE Trans. Neural Networks.

[19]  Carver Mead,et al.  Analog VLSI and neural systems , 1989 .

[20]  Misha Anne Mahowald,et al.  VLSI analogs of neuronal visual processing: a synthesis of form and function , 1992 .

[21]  X. Arreguit,et al.  A CMOS motion detector system for pointing devices , 1996, 1996 IEEE International Solid-State Circuits Conference. Digest of TEchnical Papers, ISSCC.