Impact of increasing number of neurons on performance of neuromorphic architecture

Pattern recognition is used to classify the input data into different classes based on extracted key features. Increasing the recognition rate of pattern recognition applications is a challenging task. The spike neural networks inspired from physiological brain architecture, is a neuromorphic hardware implementation of network of neurons. A sample of neuromorphic architecture has two layers of neurons, input and output. The number of input neurons is fixed based on the input data patterns. While the number of outputs neurons can be different. The goal of this paper is performance evaluation of neuromorphic architecture in terms of recognition rates using different numbers of output neurons. For this purpose a simulation environment of N2S3 and MNIST handwritten digits are used. Our simulation results show the recognition rate for various number of output neurons, 20, 30, 50, 100, 200, and 300 is 70%, 74%, 79%, 85%, 89%, and 91%, respectively.

[1]  K. Gnana Sheela,et al.  Review on Methods to Fix Number of Hidden Neurons in Neural Networks , 2013 .

[2]  Wolfgang Maass,et al.  STDP enables spiking neurons to detect hidden causes of their inputs , 2009, NIPS.

[3]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[4]  Matthew Cook,et al.  Unsupervised learning of digit recognition using spike-timing-dependent plasticity , 2015, Front. Comput. Neurosci..

[5]  T. Serrano-Gotarredona,et al.  STDP and STDP variations with memristors for spiking neuromorphic learning systems , 2013, Front. Neurosci..

[6]  Yue Liu,et al.  Optimizing number of hidden neurons in neural networks , 2007, Artificial Intelligence and Applications.

[7]  J. Grollier,et al.  A ferroelectric memristor. , 2012, Nature materials.

[8]  Andrew S. Cassidy,et al.  A million spiking-neuron integrated circuit with a scalable communication network and interface , 2014, Science.

[9]  Rodrigo Alvarez-Icaza,et al.  Neurogrid: A Mixed-Analog-Digital Multichip System for Large-Scale Neural Simulations , 2014, Proceedings of the IEEE.

[10]  Steven J. Plimpton,et al.  A historical survey of algorithms and hardware architectures for neural-inspired and neuromorphic computing applications , 2017, BICA 2017.

[11]  Michael L. Hines,et al.  NEURON — A Program for Simulation of Nerve Equations , 1993 .

[12]  E. Vianello,et al.  Bio-Inspired Stochastic Computing Using Binary CBRAM Synapses , 2013, IEEE Transactions on Electron Devices.

[13]  Eugene M. Izhikevich,et al.  Simple model of spiking neurons , 2003, IEEE Trans. Neural Networks.

[14]  Pierre Boulet,et al.  N2S3, a Simulator for the Architecture Exploration of Neuromorphic Accelerators , 2015 .

[15]  D. Johnston,et al.  Regulation of Synaptic Efficacy by Coincidence of Postsynaptic APs and EPSPs , 1997 .

[16]  A. Hodgkin,et al.  A quantitative description of membrane current and its application to conduction and excitation in nerve , 1990 .

[17]  Paolo Fantini,et al.  Unsupervised Learning by Spike Timing Dependent Plasticity in Phase Change Memory (PCM) Synapses , 2016, Front. Neurosci..

[18]  Dong Wang,et al.  Development of a neuromorphic computing system , 2015, 2015 IEEE International Electron Devices Meeting (IEDM).

[19]  M. Ueda,et al.  Artificial synapses using ferroelectric memristors embedded with CMOS Circuit for image recognition , 2014, 72nd Device Research Conference.

[20]  J. Yang,et al.  Memristive switching mechanism for metal/oxide/metal nanodevices. , 2008, Nature nanotechnology.

[21]  Pierre Boulet,et al.  Unconventional digital computing approach: memristive nanodevice platform , 2015 .

[22]  Cong Xu,et al.  Design implications of memristor-based RRAM cross-point structures , 2011, 2011 Design, Automation & Test in Europe.

[23]  Farnood Merrikh-Bayat,et al.  Training and operation of an integrated neuromorphic network based on metal-oxide memristors , 2014, Nature.

[24]  Vittorio Dante,et al.  A VLSI recurrent network of integrate-and-fire neurons connected by plastic synapses with long-term memory , 2003, IEEE Trans. Neural Networks.

[25]  Wei Yang Lu,et al.  Nanoscale memristor device as synapse in neuromorphic systems. , 2010, Nano letters.

[26]  B. Rajendran,et al.  Neuromorphic Computing Based on Emerging Memory Technologies , 2016, IEEE Journal on Emerging and Selected Topics in Circuits and Systems.

[27]  L. Chua.  Memristor-The missing circuit element , 1971 .

[28]  Damien Querlioz,et al.  Design exploration methodology for memristor-based spiking neuromorphic architectures with the Xnet event-driven simulator , 2013, 2013 IEEE/ACM International Symposium on Nanoscale Architectures (NANOARCH).

[29]  Carver A. Mead,et al.  Neuromorphic electronic systems , 1990, Proc. IEEE.

[30]  Steve B. Furber,et al.  The SpiNNaker Project , 2014, Proceedings of the IEEE.

[31]  Pierre Boulet,et al.  Parameter Exploration to Improve Performance of Memristor-Based Neuromorphic Architectures , 2018, IEEE Transactions on Multi-Scale Computing Systems.

[32]  Qi Liu,et al.  Controllable growth of nanoscale conductive filaments in solid-electrolyte-based ReRAM by using a metal nanocrystal covered bottom electrode. , 2010, ACS nano.

[33]  Anthony S. Maida,et al.  A Minimal Spiking Neural Network to Rapidly Train and Classify Handwritten Digits in Binary and 10-Digit Tasks , 2015 .

[34]  Wulfram Gerstner,et al.  Why spikes? Hebbian learning and retrieval of time-resolved excitation patterns , 1993, Biological Cybernetics.

[35]  Tobi Delbruck,et al.  Real-time classification and sensor fusion with a spiking deep belief network , 2013, Front. Neurosci..

[36]  Yuxiao Hu,et al.  Learning a Spatially Smooth Subspace for Face Recognition , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[37]  Chung Lam,et al.  Brain-like associative learning using a nanoscale non-volatile phase change synaptic device array , 2014, Front. Neurosci..

[38]  Pierre Boulet,et al.  Combining a volatile and nonvolatile memristor in artificial synapse to improve learning in Spiking Neural Networks , 2016, 2016 IEEE/ACM International Symposium on Nanoscale Architectures (NANOARCH).

[39]  Hao Yu,et al.  Selection of Proper Neural Network Sizes and Architectures—A Comparative Study , 2012, IEEE Transactions on Industrial Informatics.

[40]  Shih-Chii Liu,et al.  Temporal coding in a silicon network of integrate-and-fire neurons , 2004, IEEE Transactions on Neural Networks.

[41]  Marc-Oliver Gewaltig,et al.  NEST (NEural Simulation Tool) , 2007, Scholarpedia.

[42]  Romain Brette,et al.  Neuroinformatics Original Research Article Brian: a Simulator for Spiking Neural Networks in Python , 2022 .