Dissertation > Excellent graduate degree dissertation topics show

A New Algorithm of Spiking Neural Networks Involving Derivative of State Function

Author: YangWenYu
Tutor: WuWei
School: Dalian University of Technology
Course: Computational Mathematics
Keywords: Spiking neuron Firing time Derivative of the state function Error-Backpropagation Algorithm Differentiation of the firing time with respect to the state
CLC: TP183
Type: PhD thesis
Year: 2013
Downloads: 91
Quote: 0
Read: Download Dissertation

Abstract


Spiking neural networks (SNNs) are more biologically plausible and are often referred to as the third generation of neural networks. SNNs have experienced an increasingly large amount of research attention. Information processing with classical neural networks based on the frequency of spike emission may lose information, which leads to the investigation of spiking neural networks. In SNNs, the real world information is interpreted as spike time, which makes SNNs have a possibility to fast decode information and have a special advantage to process temporal problems. A spiking neuron receives input vector of spike times, and activates a state function by increasing the time until the value of the state function reaches certain threshold value at a firing time. And the firing time is the output of the spiking neuron. SNNs have been applied extensively and successfully for practical application such as auto-associator, pattern recognition, classification and clustering.The numerous potential advantages of SNNs have been widely discussed, such as com-putational complexity, learnability and temporal data processing. However, the computational power of SNNs is still hard to control, so that efficient network models and algorithms remain to be discovered. From the view of mathematics people, we propose a modified spiking neu-ron and give a corresponding learning algorithm. The single modified spiking neuron can solve the problems solved by usual neural networks with hidden layer. Furthermore, we propose a one-layer modified spiking neural network using the modified neuron as the building block. In addition, we give the proof of the key formula in the learning algorithm of SNNs. The main results of this dissertation can be summarized as follows:1. In Chapter2, we propose, and investigate the performance of, a modified spiking neuron, of which the output is a linear combination of the firing time ta and the derivative x’(ta). An advantage of the modified spiking neuron is shown by the fact that the XOR problem can be solved by a single modified spiking neuron, but not by the classical spiking perceptron or the usual feedforward perceptron. Furthermore, somehow surprising advantage of the modified spiking neuron is that the performance of the single modified spiking neuron is comparable to a usual spiking neural network with a hidden layer for solving some benchmark problems. 2. In Chapter3, we propose, and investigate the performance of, a modifide one-layer spiking neural network using the modified neuron as the building block. It is shown by numerical experiments that a modified one-layer spiking neural network using same or fewer encod-ing neurons is almost as good as a usual spiking neural network with a hidden layer for performing classification on real-world data.3. In Chapter4, we prove a key formula in the learning algorithm of spiking neural network, without the help of the linearity assumption between the state function and the time around the firing time.

Related Dissertations

  1. Time Series Analysis on Stochastic and Chaotic Neural Firing Rhythms,Q424
  2. Characteristics of the semiconductor bridge and its laws,TN303
  3. Design of Weapon Detection Device Control System,TP183
  4. Process Support Vector Machine and Its Application to Satellite Thermal Equilibrium Temperature Prediction,TP183
  5. Research on Anti-periodic Solutions of Delayed Cellular Neural Networks without Assuming Global Lipschitz Conditions,TP183
  6. The Identification of Fault Type in Transmission Lines Based on Neural Network,TP183
  7. The Optimization Research of Feedforward Neural Network Based on Genetic Algorithms,TP183
  8. Based on Fuzzy Neural Network Fault Diagnosis of Expert Systems,TP183
  9. Non-linear Time-Varying System Modeling Using Time-Varying High-Order Neural Networks,TP183
  10. Design of Positive Draw-back Motion of Wool Spinning Frame and Comparison of Prediction Models of Worsted Yarns Performances,TP183
  11. Software Project Risk Assessment Based on BP Neural Networks,TP183
  12. Soft-measuring of Hot-rolled Strip’s Mechanical Properties Based on Improved BP Algorithm,TP183
  13. Research on Neural Network Based Power Transformer Fault Forecast Model,TP183
  14. Rules Extraction from Artificial Neural Networks for Classification Based Improvedant Colony Algorithm,TP183
  15. Research on the Building Foundation Settlement Prediction by Wavelet Neural Network,TP183
  16. Research of Adaptive Active Noise Control Based on Neural Network,TP183
  17. The Condition Monitor and Diagnostic of ANSTEEL Blast Furnace Blowers Base on the Neural Network,TP183
  18. Dynamical Hehavior of a Class of Competivie Neural Networks with Distrbuted Tiem Delys,TP183
  19. On the BP Algorithm: A Regularization Approach,TP183
  20. Based on Neural Network Model of Hot-rolling,TP183
  21. Application of the BP ANN in the Spunmelt Nonwoven Product development,TP183

CLC: > Industrial Technology > Automation technology,computer technology > Automated basic theory > Artificial intelligence theory > Artificial Neural Networks and Computing
© 2012 www.DissertationTopic.Net  Mobile