Dissertation > Excellent graduate degree dissertation topics show
Sensitivity Study and Application of Complex Variabal Weight Function Neural Network
Author: DingMan
Tutor: ZhangDaiYuan
School: Nanjing University of Posts and Telecommunications
Course: Applied Computer Technology
Keywords: Neural Networks Complex variable weight function Complex variable approximation Sensitivity Spectrum shaping
CLC: TP183
Type: Master's thesis
Year: 2012
Downloads: 11
Quote: 0
Read: Download Dissertation
Abstract
|
Monograph \This new concept can overcome the defects of traditional neural network training , while avoiding local minima , slow convergence many shortcomings . Complex variable weighting function neural network is a complex field expansion , so it has all the benefits of the weight function neural network . The sensitivity of the neural network , but also has important research significance . Calculate the weight function of the neural network in the training , the network output by the surrounding environment and input disturbances can be drawn through the sensitivity analysis . In this paper, the neural network sensitivity analysis as the premise , in-depth study of the network model error and approximation noise error , and thus to study the sensitivity of the complex variable weighting function neural network , and derived formula . The article first introduces the representation of complex function of variable weights ; then introduce the weight function neural network sensitivity statistical definition ; then study network model error noise and approximation error and eventually come to the sensitivity of the complex variable weighting function neural network . Meanwhile, on the basis of theoretical analysis using Matlab tools and simulation of complex variable weighting function neural network and its sensitivity , through the analysis of simulation results verify the validity and correctness of the theoretical analysis . The sensitivity of the use of complex variable weighting function neural network , this paper design a cognitive radio spectrum shaping . Based on the theoretical analysis , to design a model of the spectrum shaping circumvention band ; thus calculate the system 's sensitivity to achieve reliable spectrum sharing . Finally, after the experimental simulation validation, combined with the complex variable weighting function neural network sensitivity spectrum shaping in the effective use of spectrum and avoid spectrum collisions have better results.
|
Related Dissertations
- The Effect of Composite Additive on the SNCR,X701
- High Speed Frequency Measurment and Non-Linearity Correction of Frequency Modulated Capacitive Displacement Sensor,TH822
- Study on a Pneumatic Manipulator Clamping Force Control System Based on H ∞ Control Theory,TP241
- Research on Anti-periodic Solutions of Delayed Cellular Neural Networks without Assuming Global Lipschitz Conditions,TP183
- Designs and Applications of Fuzzy Synthetic Evaluation Models Based on Parallel Algorithms,TP18
- Preparation and Properties of Chitosan-based Thermosensitive Composite Hydrogel,R943
- Isolation and Identification of Avian Pathogenic Escherichia Coli from Chicken and Characterizations of Its Virulence-Associated Genes,S852.61
- Cloning and Characterization of Photoperiod Sensitive Gene ZmELF4 in Maize,S513
- Spectrum Variation of Vegetation in Yanzhou Coal Mine Area and Heavy Metal Stress Characteristic,X173
- Change and Value of Serum Soluble Lectin-Like Oxidized Low-Density Lipoprotein Receptor-1 in Acute Coronary Syndrome,R541.4
- Effects of Telmisartan on hs-CRP and HMW-adiponectinin Patients with Essential Hypertension,R544.1
- Study on Clinical Value of High-sensitivity Cardiac Troponin T Assay in Myocardial Infarction,R542.22
- Correlation Analysis between Coronary Lesion Severity and Peripheral Blood Cell CD34~+ Ratio in the Coronary Heart Disease Patients Complicating Diabetes Mellitus,R541.4
- Application and Significance of CISS Classification and TOAST Subtype on Ischemic Stroke (Attach 210 Cases Analysis),R743.3
- Ischemic stroke and carotid atherosclerosis and related biochemical hs-CRP and LDL-C changes,R743.3
- Individuals with type 2 diabetes, serum complement factor H, hs-CRP levels and insulin resistance study,R587.1
- Aloe anthraquinones enhanced UV radiation on plant protection,X173
- Automatic Calibration System Voltage Monitor,TM933.2
- Research on NO-reference Image Quality Assessment Based on HVS,TP391.41
- Study of Static and Dynamic Collaborative Optimization on Container Ship Structure,U674.131
- Multi- license plate location method based on CNN's Intelligent Transportation Systems Research,TP391.41
CLC: > Industrial Technology > Automation technology,computer technology > Automated basic theory > Artificial intelligence theory > Artificial Neural Networks and Computing
© 2012 www.DissertationTopic.Net Mobile
|