A Minimal Spiking Neural Network to Rapidly Train and Classify Handwritten Digits in Binary and 10-Digit Tasks
Journal Title: International Journal of Advanced Research in Artificial Intelligence(IJARAI) - Year 2015, Vol 4, Issue 7
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
- EP ID EP127465
- DOI 10.14569/IJARAI.2015.040701
- Views 126
- Downloads 0
Temperature Control System Using Fuzzy Logic Technique
Fuzzy logic technique is an innovative technology used in designing solutions for multi-parameter and non-linear control models for the definition of a control strategy. As a result, it delivers solutions faster th...
Dynamic Programming Method Applied in Vietnamese Word Segmentation Based on Mutual Information among Syllables
Vietnamese word segmentation is an important step in Vietnamese natural language processing such as text categorization, text summary, and automated machine translation. The problem with Vietnamese word segmentatio...
Algorithm for Design of Digital Notch Filter Using Simulation
A smooth waveform is generated of low frequency signal can be achieved through the Digital Notch Filter. Noise can be easily eliminated from a speech signal by using a Notch filter. In this paper the design of notch filt...
A Minimal Spiking Neural Network to Rapidly Train and Classify Handwritten Digits in Binary and 10-Digit Tasks
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...
Estimation of soil moisture in paddy field using Artificial Neural Networks
In paddy field, monitoring soil moisture is required for irrigation scheduling and water resource allocation, management and planning. The current study proposes an Artificial Neural Networks (ANN) model to estima...