Spike timing dependent plasticity (STDP) can ameliorate process variations in neuromorphic VLSI

A transient-detecting very large scale integration (VLSI) pixel is described, suitable for use in a visual-processing, depth-recovery algorithm based upon spike timing. A small array of pixels is coupled to an adaptive system, based upon spike timing dependent plasticity (STDP), that aims to reduce the effect of VLSI process variations on the algorithm's performance. Results from 0.35 /spl mu/m CMOS temporal differentiating pixels and STDP circuits show that the system is capable of adapting to substantially reduce the effects of process variations without interrupting the algorithm's natural processes. The concept is generic to all spike timing driven processing algorithms in a VLSI.

[1]  L. M. Terman,et al.  A 1 mV MOS Comparator , 1977, ESSCIRC '77: 3rd European Solid State Circuits Conference.

[2]  Misha Mahowald,et al.  A Spike Based Learning Neuron in Analog VLSI , 1996, NIPS.

[3]  G. Wegmann,et al.  Basic principles of accurate dynamic current mirrors , 1990 .

[4]  Wulfram Gerstner,et al.  Hebbian learning of pulse timing in the Barn Owl auditory system , 1999 .

[5]  Florentin Wörgötter,et al.  A Parallel Noise-Robust Algorithm to Recover Depth Information from Radial Flow Fields , 1999, Neural Computation.

[6]  Alan F. Murray,et al.  Can spike timing dependent plasticity compensate for process mismatch in neuromorphic analogue VLSI? , 2004, 2004 IEEE International Symposium on Circuits and Systems (IEEE Cat. No.04CH37512).

[7]  Alan F. Murray,et al.  Learning temporal correlations in biologically-inspired aVLSI , 2003, Proceedings of the 2003 International Symposium on Circuits and Systems, 2003. ISCAS '03..

[8]  Jack D. Cowan,et al.  DYNAMICS OF SELF-ORGANIZED DELAY ADAPTATION , 1999 .

[9]  Bernard Courtois,et al.  Design of an APS CMOS Image Sensor for Low Light Level Applications Using Standard CMOS Technology , 2001 .

[10]  Wulfram Gerstner,et al.  What is Different with Spiking Neurons , 2001 .

[11]  Giacomo Indiveri.  Neuromorphic Bisable VLSI Synapses with Spike-Timing-Dependent Plasticity , 2002, NIPS 2002.

[12]  Tobi Delbrück,et al.  Adaptive photoreceptor with wide dynamic range , 1994, Proceedings of IEEE International Symposium on Circuits and Systems - ISCAS '94.

[13]  Paul E. Hasler,et al.  Biological learning modeled in an adaptive floating-gate system , 2002, 2002 IEEE International Symposium on Circuits and Systems. Proceedings (Cat. No.02CH37353).

[14]  Giacomo Indiveri,et al.  A VLSI reconfigurable network of integrate-and-fire neurons with spike-based learning synapses , 2004, ESANN.

[15]  Alan F. Murray,et al.  Citcuits for VLSI Implementation of Temporally Asymmetric Hebbian Learning , 2001, NIPS.

[16]  Alan F. Murray,et al.  Synchrony detection and amplification by silicon neurons with STDP synapses , 2004, IEEE Transactions on Neural Networks.

[17]  P. Deval,et al.  Very accurate current divider , 1989 .

[18]  F. Forti,et al.  Measurement of MOS current mismatch in the weak inversion region , 1994, IEEE J. Solid State Circuits.

[19]  Marcel J. M. Pelgrom,et al.  Matching properties of MOS transistors , 1989 .

[20]  Jörg Kramer,et al.  An integrated optical transient sensor , 2002 .

[21]  Giacomo Indiveri,et al.  Neuromorphic Bistable VLSI Synapses with Spike-Timing-Dependent Plasticity , 2002, NIPS.

[22]  Alan F. Murray,et al.  Synchrony Detection by Analogue VLSI Neurons with Bimodal STDP Synapses , 2003, NIPS.

[23]  Günther Palm,et al.  Synaptic Delay Learning in Pulse-Coupled Neurons , 1998, Neural Computation.