Function approximation with uncertainty propagation in a VLSI spiking neural network

The brain combines and integrates multiple cues to take coherent, context-dependent action using distributed, event-based computational primitives. Computational models that use these principles in software simulations of recurrently coupled spiking neural networks have been demonstrated in the past, but their implementation in hybrid analog/digital Very Large Scale Integration (VLSI) spiking neural networks remains challenging. Here, we demonstrate a distributed spiking neural network architecture comprising multiple neuromorphic VLSI chips able to reproduce these types of cue combination and integration operations. This is achieved by encoding cues as population activities of input nodes in a network of recurrently coupled VLSI Integrate-and-Fire (I&F) neurons. The value of the cue is place-encoded, while its uncertainty is represented by the width of the population activity profile. Relationships among different cues are specified through bidirectional connectivity matrices, shared between the individual input node populations and an intermediate node population. The resulting network dynamics bidirectionally relate not only the values of three variables according to a specified relation, but also their uncertainties. When cues on two populations are specified, the standard deviation of the activity in the unspecified population varies approximately linearly with the widths of the two input cues, and has less than 6% error in position compared to the value specified by the inputs. The results suggest a mechanism for recurrently relating cues such that missing information can both be recovered and assigned a level of certainty.

[1]  R. Douglas,et al.  A Quantitative Map of the Circuit of Cat Primary Visual Cortex , 2004, The Journal of Neuroscience.

[2]  L F Abbott,et al.  Coordinate transformations in the visual system: how to generate gain fields and what to compute with them. , 2001, Progress in brain research.

[3]  Mingqi Deng,et al.  Winner-take-all networks , 1992 .

[4]  Matthew Cook,et al.  Unsupervised Learning of Relations , 2010, ICANN.

[5]  T. Sejnowski,et al.  Correlated neuronal activity and the flow of neural information , 2001, Nature Reviews Neuroscience.

[6]  Matthew Cook,et al.  Real-time inference in a VLSI spiking neural network , 2012, 2012 IEEE International Symposium on Circuits and Systems.

[7]  Giacomo Indiveri,et al.  A PCI based high-fanout AER mapper with 2 GiB RAM look-up table, 0.8 µs latency and 66MHz output event-rate , 2011, 2011 45th Annual Conference on Information Sciences and Systems.

[8]  Wei Ji Ma,et al.  Bayesian inference with probabilistic population codes , 2006, Nature Neuroscience.

[9]  Timothy D. Hanks,et al.  Probabilistic Population Codes for Bayesian Decision Making , 2008, Neuron.

[10]  Giacomo Indiveri,et al.  A device mismatch compensation method for VLSI neural networks , 2010, 2010 Biomedical Circuits and Systems Conference (BioCAS).

[11]  Jean-Jacques E. Slotine,et al.  Collective Stability of Networks of Winner-Take-All Circuits , 2011, Neural Computation.

[12]  Nicholas I. Fisher,et al.  Statistical Analysis of Circular Data , 1993 .

[13]  Rodney J. Douglas,et al.  A pulse-coded communications infrastructure for neuromorphic systems , 1999 .

[14]  R. Douglas,et al.  Neuronal circuits of the neocortex. , 2004, Annual review of neuroscience.

[15]  Chiara Bartolozzi,et al.  Selective Attention in Multi-Chip Address-Event Systems , 2009, Sensors.

[16]  A. Pouget,et al.  Efficient computation and cue integration with noisy population codes , 2001, Nature Neuroscience.