Biologically compatible neural networks with reconfigurable hardware

This paper presents a reconfigurable hardware neuro-simulator specifically designed to emulate biophysically accurate and biologically compatible neural networks. The platform is based on FPGA technology which is used to create real-time custom neuroprocessors with floating point accuracy and a novel hybrid time-event driven architecture for synaptic integration. Through a series of experiments the dynamics of the neuroprocessors are evaluated and compared with real neuron responses. The problem of interconnecting neurons with individual synapses is tackled with a novel synaptic architecture where all incoming synapses are merged efficiently in one single accumulative process without losing biological information. The case studies demonstrate the suitability of conductance-based models and FPGA platforms to simulate living organisms' behaviour in a biological compatible context.

[1]  J. Lu,et al.  A Model of a Segmental Oscillator in the Leech Heartbeat Neuronal Network , 2001, Journal of Computational Neuroscience.

[2]  H. Kager,et al.  Seizure-like afterdischarges simulated in a model neuron , 2007, Journal of Computational Neuroscience.

[3]  Joe McGeehan,et al.  Numerically efficient and biophysically accurate neuroprocessing platform , 2013, 2013 International Conference on Reconfigurable Computing and FPGAs (ReConFig).

[4]  Aubin Tchaptchet,et al.  Real-Time Simulations of Synchronization in a Conductance-Based Neuronal Network with a Digital FPGA Hardware-Core , 2012, ICANN.

[5]  A. Scott,et al.  Alwyn Scott How Smart is a Neuron ? , 2000 .

[6]  Simon W. Moore,et al.  Bluehive - A field-programable custom computing machine for extreme-scale real-time neural network simulation , 2012, 2012 IEEE 20th International Symposium on Field-Programmable Custom Computing Machines.

[7]  Georgios Smaragdos,et al.  FPGA-based biophysically-meaningful modeling of olivocerebellar neurons , 2014, FPGA.

[8]  Wayne Luk,et al.  A Large-Scale Spiking Neural Network Accelerator for FPGA Systems , 2012, ICANN.

[9]  Maizura Mokhtar,et al.  Hippocampus-Inspired Spiking Neural Network on FPGA , 2008, ICES.

[10]  Vivek K. Pallipuram,et al.  Optimization and performance study of large-scale biological networks for reconfigurable computing , 2010, 2010 FOURTH INTERNATIONAL WORKSHOP ON HIGH-PERFORMANCE RECONFIGURABLE COMPUTING TECHNOLOGY AND APPLICATIONS (HPRCTA).

[11]  Yiwei Zhang.  Biophysically accurate floating point neuroprocessors , 2011 .

[12]  B. Hille.  Ionic channels of excitable membranes , 2001 .

[13]  Tomaso Poggio,et al.  CNS: a GPU-based framework for simulating cortically-organized networks , 2010 .

[14]  Tim Gollisch,et al.  Modeling Single-Neuron Dynamics and Computations: A Balance of Detail and Abstraction , 2006, Science.

[15]  Yiwei Zhang,et al.  Biophysically Accurate Foating Point Neuroprocessors for Reconfigurable Logic , 2013, IEEE Transactions on Computers.

[16]  S. Moore,et al.  EFFICIENT HANDLING OF SYNAPTIC UPDATES IN FPGA-BASED LARGE-SCALE NEURAL NETWORK SIMULATIONS , 2012 .

[17]  Bernhard Ronacher,et al.  Neurophysiological Aspects of Song Pattern Recognition and Sound Localization in Grasshoppers , 1994 .

[18]  Tugberk Ugurlu,et al.  Optimization and Performance , 2013 .

[19]  R. Traub,et al.  A model of a CA3 hippocampal pyramidal neuron incorporating voltage-clamp data on intrinsic conductances. , 1991, Journal of neurophysiology.

[20]  Sylvain Saïghi,et al.  Leech Heartbeat Neural Network on FPGA , 2013, Living Machines.

[21]  Vincenzo Crunelli,et al.  NeuReal: An interactive simulation system for implementing artificial dendrites and large hybrid networks , 2008, Journal of Neuroscience Methods.

[22]  Anton Kulakov,et al.  Multiprocessing neural network simulator , 2013 .

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

[24]  John Rinzel,et al.  Intrinsic and network rhythmogenesis in a reduced traub model for CA3 neurons , 1995, Journal of Computational Neuroscience.

[25]  Florent de Dinechin,et al.  When FPGAs are better at floating-point than microprocessors , 2008, FPGA '08.

[26]  S. Lockery,et al.  A neural network model for chemotaxis in Caenorhabditis elegans , 2003, Proceedings of the International Joint Conference on Neural Networks, 2003..