An FPGA platform for on-line topology exploration of spiking neural networks

Abstract In this paper we present a platform for evolving spiking neural networks on FPGAs. Embedded intelligent applications require both high performance, so as to exhibit real-time behavior, and flexibility, to cope with the adaptivity requirements. While hardware solutions offer performance, and software solutions offer flexibility, reconfigurable computing arises between these two types of solutions providing a trade-off between flexibility and performance. Our platform is described as a combination of three parts: a hardware substrate, a computing engine, and an adaptation mechanism. We present, also, results about the performance and synthesis of the neural network implementation on an FPGA.

[1]  Russell Reed,et al.  Pruning algorithms-a survey , 1993, IEEE Trans. Neural Networks.

[2]  Marc Toussaint,et al.  Task-dependent evolution of modularity in neural networks , 2002 .

[3]  D. E. Goldberg,et al.  Genetic Algorithms in Search , 1989 .

[4]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[5]  Isaac Meilijson,et al.  Evolution of Reinforcement Learning in Uncertain Environments: A Simple Explanation for Complex Foraging Behaviors , 2002, Adapt. Behav..

[6]  Hussein A. Abbass,et al.  Speeding Up Backpropagation Using Multiobjective Evolutionary Algorithms , 2003, Neural Computation.

[7]  X. Yao.  Evolving Artificial Neural Networks , 1999 .

[8]  Wolfgang Maass,et al.  Networks of Spiking Neurons: The Third Generation of Neural Network Models , 1996, Electron. Colloquium Comput. Complex..

[9]  D. Signorini,et al.  Neural networks , 1995, The Lancet.

[10]  Wulfram Gerstner,et al.  SPIKING NEURON MODELS Single Neurons , Populations , Plasticity , 2002 .

[11]  Mauro Birattari,et al.  Swarm Intelligence , 2012, Lecture Notes in Computer Science.

[12]  José R. Álvarez,et al.  Artificial Neural Nets Problem Solving Methods , 2003, Lecture Notes in Computer Science.

[13]  Andrés Pérez Uribe,et al.  Structure-Adaptable Digital Neural Networks , 1999 .

[14]  S. Gould.  The Structure of Evolutionary Theory , 2002 .

[15]  Carlos Andrés Peña-Reyes,et al.  Coevolutionary Fuzzy Modeling , 2004, Lecture Notes in Computer Science.

[16]  Peña Reyes,et al.  Coevolutionary Fuzzy Modeling , 2004, Lecture Notes in Computer Science.

[17]  Christian Igel,et al.  Operator adaptation in evolutionary computation and its application to structure optimization of neural networks , 2003, Neurocomputing.

[18]  Dario Floreano,et al.  Hardware spiking neural network with run-time reconfigurable connectivity in an autonomous robot , 2003, NASA/DoD Conference on Evolvable Hardware, 2003. Proceedings..

[19]  Thomas G. Dietterich.  What is machine learning? , 2020, Archives of Disease in Childhood.

[20]  Andres Perez-Uribe,et al.  Structure-Adaptable Digital Neural Networks , 1999 .

[21]  Wulfram Gerstner,et al.  Spiking Neuron Models , 2002 .

[22]  Andres Upegui,et al.  A Hardware Implementation of a Network of Functional Spiking Neurons with Hebbian Learning , 2004, BioADIT.

[23]  Eduardo Ros,et al.  Post-synaptic Time-Dependent Conductances in Spiking Neurons: FPGA Implementation of a Flexible Cell Model , 2003, IWANN.

[24]  Dario Floreano,et al.  Evolutionary robots with on-line self-organization and behavioral fitness , 2000, Neural Networks.

[25]  Michael D. Vose,et al.  The simple genetic algorithm - foundations and theory , 1999, Complex adaptive systems.

[26]  Mike Peattie.  Two Flows for Partial Reconfiguration: Module Based or Small Bit Manipulations , 2000 .

[27]  Wofgang Maas,et al.  Networks of spiking neurons: the third generation of neural network models , 1997 .

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

[29]  ScienceDirect.  Microprocessors and microsystems , 1978 .

[30]  Christopher J. Bishop,et al.  Pulsed Neural Networks , 1998 .

[31]  Jan Eriksson,et al.  Hardware Optimization of a Novel Spiking Neuron Model for the POEtic Tissue , 2009, IWANN.

[32]  S. Hyakin,et al.  Neural Networks: A Comprehensive Foundation , 1994 .

[33]  Christopher G. Langton,et al.  Artificial Life , 2019, Philosophical Posthumanism.

[34]  Andres Upegui,et al.  An Functional Spiking Neuron Hardware Oriented Model , 2003, IWANN.