Real-time multi-board architecture for analog spiking neural networks

In this paper, we present a multi-board system based on analog neuromimetic ICs. These ICs compute in realtime conductance-based models. These models are implemented in a modular architecture based on our analog IPs. Each IC includes five neurons and analog memory cells to set and store the conductance model parameters, and eventually optimize it to compensate the analog circuit variability. The circuits are embedded in a multi-board system able to host up to 120 neurons spread across 6 boards all connected to a backplane with daisy-chain facilities. Each action potential computed by analog neuromimetic chips is time-stamped when detected by digital device (FPGA). These FPGAs are also in charge of the real-time plasticity computation and of controlling inter-boards communication. The system is designed to compute programmable models and connectivity schemes.

[1]  Gert Cauwenberghs,et al.  Dynamically Reconfigurable Silicon Array of Spiking Neurons With Conductance-Based Synapses , 2007, IEEE Transactions on Neural Networks.

[2]  Johannes Schemmel,et al.  Modeling Synaptic Plasticity within Networks of Highly Accelerated I&F Neurons , 2007, 2007 IEEE International Symposium on Circuits and Systems.

[3]  Giacomo Indiveri,et al.  A VLSI array of low-power spiking neurons and bistable synapses with spike-timing dependent plasticity , 2006, IEEE Transactions on Neural Networks.

[4]  Yannick Bornat,et al.  Design of Analog/Digital Simulator Dedicated to Real-time Neurocomputing , 2007 .

[5]  Yannick Bornat,et al.  A Library of Analog Operators Based on the Hodgkin-Huxley Formalism for the Design of Tunable, Real-Time, Silicon Neurons , 2011, IEEE Transactions on Biomedical Circuits and Systems.

[6]  O. Malot,et al.  Token-passing communication protocol in hardware-based real-time spiking neural networks , 2009, Microtechnologies.

[7]  Henry Markram,et al.  Minimal Hodgkin–Huxley type models for different classes of cortical and thalamic neurons , 2008, Biological Cybernetics.

[8]  Ralph Etienne-Cummings,et al.  Configuring silicon neural networks using genetic algorithms , 2008, 2008 IEEE International Symposium on Circuits and Systems.

[9]  S. Renaud,et al.  Automated tuning of analog neuromimetic integrated circuits , 2009, 2009 IEEE Biomedical Circuits and Systems Conference.

[10]  Terrence J. Sejnowski,et al.  An Efficient Method for Computing Synaptic Conductances Based on a Kinetic Model of Receptor Binding , 1994, Neural Computation.

[11]  E. Marder,et al.  Plasticity in single neuron and circuit computations , 2004, Nature.

[12]  Kwabena Boahen,et al.  Learning in Silicon: Timing is Everything , 2005, NIPS.