A Minimal Spiking Neural Network to Rapidly Train and Classify Handwritten Digits in Binary and 10-Digit Tasks

Abstract

 This paper reports the results of experiments to develop a minimal neural network for pattern classification. The network uses biologically plausible neural and learning mechanisms and is applied to a subset of the MNIST dataset of handwritten digits. The research goal is to assess the classification power of a very simple biologically motivated mechanism. The network architecture is primarily a feedforward spiking neural network (SNN) composed of Izhikevich regular spiking (RS) neurons and conductance-based synapses. The weights are trained with the spike timing-dependent plasticity (STDP) learning rule. The proposed SNN architecture contains three neuron layers which are connected by both static and adaptive synapses. Visual input signals are processed by the first layer to generate input spike trains. The second and third layers contribute to spike train segmentation and STDP learning, respectively. The network is evaluated by classification accuracy on the handwritten digit images from the MNIST dataset. The simulation results show that although the proposed SNN is trained quickly without error-feedbacks in a few number of iterations, it results in desirable performance (97.6%) in the binary classification (0 and 1). In addition, the proposed SNN gives acceptable recognition accuracy in 10-digit (0-9) classification in comparison with statistical methods such as support vector machine (SVM) and multi-perceptron neural network.

Authors and Affiliations

Amirhossein Tavanaei, Anthony Maida

Keywords

Related Articles

 A Method of Multi-License Plate Location in Road Bayonet Image

 To solve the problem of multi-license plate location in road bayonet image, a novel approach was presented, which utilized plate’s color features, geometry characteristics and gray feature. Firstly, the RGB color i...

 Experimental Approach of Reflectance Based Vicarious Calibration Method for Solar Reflectance Wavelength Region of Sensor Onboard Remote Sensing Satellites

 Experimental approach of reflectance based vicarious calibration of solar reflectance wavelength region of mission instruments onboard remote sensing satellites is conducted. As an example, vicarious calibration of...

 Regressive Analysis on Leaf Nitrogen Content and Near Infrared Reflectance and Its Application for Agricultural Farm Monitoring with Helicopter Mounted Near Infrared Camera

 Method for evaluation of nitrogen richness of tealeaves with near infrared reflectance is proposed. Also tea farm monitoring with helicopter mounted near infrared camera is proposed. Through experiments and regress...

 Parameter Optimization for Nadaraya-Watson Kernel Regression Method with Small Samples

 Many current regression algorithms have unsatisfactory prediction accuracy with small samples. To solve this problem, a regression algorithm based on Nadaraya-Watson kernel regression (NWKR) is proposed. The propos...

 System for Human Detection in Image Based on Intel Galileo

 The aim of this paper is a comparative analysis of methods for motion detection and human recognition in the image. Authors propose the own solution following the comparative analysis of current approaches. Then au...

Download PDF file
  • EP ID EP127465
  • DOI 10.14569/IJARAI.2015.040701
  • Views 129
  • Downloads 0

How To Cite

Amirhossein Tavanaei, Anthony Maida (2015).  A Minimal Spiking Neural Network to Rapidly Train and Classify Handwritten Digits in Binary and 10-Digit Tasks. International Journal of Advanced Research in Artificial Intelligence(IJARAI), 4(7), 1-8. https://europub.co.uk/articles/-A-127465