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
Blocking Black Area Method for Speech Segmentation
Speech segmentation is an important sub problem of automatic speech recognition. This research is concerned with the development of a continuous speech segmentation system using Bangla Language. This paper presents...
The Mobile Version of the Predicted Energy Efficient Bee-Inspired Routing (PEEBR)
In this paper, the previously proposed Predictive Energy Efficient Bee-inspired Routing (PEEBR) family of routing optimization algorithms based on the Artificial Bees Colony (ABC) Optimization model is extended fro...
Evaluating Sentiment Analysis Methods and Identifying Scope of Negation in Newspaper Articles
Automatic detection of linguistic negation in free text is a demanding need for many text processing applications including Sentiment Analysis. Our system uses online news archives from two different resources name...
Method for object motion characteristic estimation based on wavelet Multi-Resolution Analysis: MRA
Method for object motion characteristic estimation based on wavelet Multi-Resolution Analysis: MRA is proposed. With moving pictures, the motion characteristics, direction of translation, roll/pitch/yaw rotations can be...
Sea Ice Concentration Estimation Method with Satellite Based Visible to Near Infrared Radiometer Data Based on Category Decomposition
Unmixing method for estimation of mixing ratio of the components of which the pixel in concern consists based on inversion theory is proposed together with its application to sea ice estimation method with satellit...