An Improved Maximum Neural Network with Stochastic Dynamics Characteristic for Maximum Clique Problem
スポンサーリンク
概要
- 論文の詳細を見る
Through analyzing the dynamics characteristic of maximum neural network with an added vertex, we find that the solution quality is mainly determined by the added vertex weights. In order to increase maximum neural network ability, a stochastic nonlinear self-feedback and flexible annealing strategy are embedded in maximum neural network, which makes the network more powerful to escape local minima and be independent of the initial values. Simultaneously, we present that solving ability of maximum neural network is dependence on problem. We introduce a new parameter into our network to improve the solving ability. The simulation in k random graph and some DIMACS clique instances in the second DIMACS challenge shows that our improved network is superior to other algorithms in light of the solution quality and CPU time.
- 社団法人 電気学会の論文
- 2008-01-01
著者
-
TANG Zheng
Faculty of Engineering, Toyama University
-
Tang Zheng
Faculty Of Engineering Toyama University
-
Tang Zheng
Univ. Toyama Toyama‐shi Jpn
-
Tang Zheng
Faculty Of Engineering Miyazaki University
-
TANG Zheng
Graduate School of Innovative Life Science, University of Toyama
-
DAI Hongwei
Faculty of Engineering, Toyama University
-
Tang Zheng
Univ. Of Toyama Toyama‐shi Jpn
-
Tang Zheng
Graduate School Of Innovative Life Science University Of Toyama
-
YANG Gang
Faculty of Engineering, Toyama University
-
Dai Hongwei
School Of Computer Engineering Huaihai Institute Of Technology
-
Dai Hongwei
Faculty Of Engineering Toyama University
-
Yang Gang
Faculty Of Engineering Toyama University
-
Tang Zheng
Department Of Computer Science And Technology The Key Laboratory Of Embedded System And Service Comp
関連論文
- Multilayer Network Learning Algorithm Based on Pattern Search Method(Neural Networks and Bioengineering)
- A Local Search Based Learning Method for Multiple-Valued Logic Networks(Neural Networks and Bioengineering)
- A Method of Learning for Multi-Layer Networks
- A Parallel Graph Planarization Algorithm Using Gradient Ascent Learning of Hopfield Network
- A Saturation Computation Method of Artificial Binary Neural Networks for Combinatorial Optimization Problems
- Local Search with Probabilistic Modeling for Learning Multiple-Valued Logic Networks
- A Fast and Reliable Approach to TSP using Positively Self-feedbacked Hopfield Networks
- Objective Function Adjustment Algorithm for Combinatorial Optimization Problems(Numerical Analysis and Optimization)
- An Improved Artificial Immune Network Model(Neural Networks and Bioengineering)
- A Neural-based Algorithm for Topological Via-minimization Problem
- A New Method to Solve the Constraint Satisfaction Problem Using the Hopfield Neural Network
- An Artificial Immune Network with Multi-layered B Cells Architecture
- An Artificial Immune System Architecture and Its Applications(Neural Networks and Bioengineering)
- The Fuzzy Immune Network and Its Application to Pattern Recognition(Special Section on Papers Selected from ITC-CSCC 2002)
- Design and realization of a network security model
- Affinity Based Lateral Interaction Artificial Immune System(Human-computer Interaction)
- Avoiding the Local Minima Problem in Backpropagation Algorithm with Modified Error Function(Neural Networks and Bioengineering)
- An Engineering Immune Network Model for Pattern Recognition
- Pattern Classification Using A Fuzzy Immune Network Model
- D-2-6 A Parallel Direct Search Learning Algorithm for Feed-Forward Neural Networks
- A Multi-Layered Immune System for Graph Planarization Problem
- An Improved Maximum Neural Network with Stochastic Dynamics Characteristic for Maximum Clique Problem
- An Artificial Immune System with Feedback Mechanisms for Effective Handling of Population Size
- A Near-Optimum Parallel Algorithm for a Graph Layout Problem(Neural Networks and Bioengineering)
- Learning Method of Hopfield Neural Network and Its Application to Traveling Salesman Problem (特集:論文誌C発刊30周年記念)
- A Multiple-Valued Immune Network and Its Applications
- Neuron-MOS Current Mirror Circuit and Its Application to Multi-Valued Logic (Special Issue on Multiple-Valued Logic and Its Applications)
- A 1-V, 1-V_ Input Range, Four-Quadrant Analog Multiplier Using Neuron-MOS Transistors
- Ultra-Low Power Two-MOS Virtual-Short Circuit and Its Application
- 自己学習ファジ-コントロ-ラ
- High accuracy microprocessor controlled sine-wave generator
- Design and Implementation of a Calibrating T-Model Neural-Based A/D Converter
- Hopfield Neural Network Learning Using Direct Gradient Descent of Energy Function
- Implementation of T-Model Neural-Based PCM Encoders Using MOS Charge-Mode Circuits
- A Learning Fuzzy Network and Its Applications to Inverted Pendulum System
- An Elastic Net Learning Algorithm for Edge Linking of Images
- Solving Maximum Cut Problem Using Improved Hop field Neural Network
- A Near-Optimum Parallel Algorithm for Bipartite Subgraph Problem Using the Hopfield Neural Network Learning
- Quantum Interference Crossover-Based Clonal Selection Algorithm and Its Application to Traveling Salesman Problem
- An Efficient Neural Algorithm for Two-layer Planarization Problem in Graph Drawing
- An Improved Local Search Learning Method for Multiple-Valued Logic Network Minimization with Bi-objectives
- An Expanded Lateral Interactive Clonal Selection Algorithm and Its Application
- Improved Clonal Selection Algorithm Combined with Ant Colony Optimization
- An Improved Clonal Selection Algorithm and Its Application to Traveling Salesman Problems(Neural Networks and Bioengineering)
- A Novel Clonal Selection Algorithm and Its Application to Traveling Salesman Problem(Neural Networks and Bioengineering)
- A stochastic dynamic local search method for learning Multiple-Valued Logic networks
- An Improved Artificial Immune System (AIS) by Considering Different Affinities among Th Cells and Antigens
- Multiple-Valued Static Random-Access-Memory Design and Application : Special Issue on Multiple-Valued integrated Circuits
- A Chaotic Clonal Selection Algorithm and its Application to Synthesize Multiple-Valued Logic Functions
- An Efficient Algorithm for Minimum Vertex Cover Problem
- Two-Phase Pattern Search-based Learning Method for Multi-layer Neural Network
- A Chaotic Maximum Neural Network for Maximum Clique Problem(Biocybernetics, Neurocomputing)
- A Parallel Graph Planarization Algorithm Using Gradient Ascent Learning of Hopfield Network
- An Efficient Algorithm for Maximum Clique Problem Using Improved Hopfield Neural Network
- A Saturation Computation Method of Artificial Binary Neural Networks for Combinatorial Optimization Problems
- A Hopfield Network Learning Algorithm for Graph Planarization
- A Gradient Ascent Learning Algorithm for Elastic Nets
- Hybrid Uniform Distribution of Particle Swarm Optimizer
- Local Search with Probabilistic Modeling for Learning Multiple-Valued Logic Networks
- A Modified Hopfield Neural Network for the Minimum Vertex Cover Problem
- An Improved Transiently Chaotic Neural Network with Application to the Maximum Clique Problems
- An Elastic Net Learning Algorithm for Edge Linking of Images(Neural Netoworks and Bioengineering)
- A Novel Maximum Neural Network with Stochastic Dynamics for N-Queens Problems
- A Child Verb Learning Model Based on Syntactic Bootstrapping
- A study of chinese accounting system
- T-model natural network for PCM encoding
- Design and Implementations of a Learning T-Model Neural Network
- An MOS four-quadrant analog multiplier using +-0.75-V power supply
- A fully-piped multiplier using the redundant binary addition tree
- Investigation and Analysis of Hysteresis in Hopfield and T-Model Neural Networks
- T-Model Neural Network for PCM Encoding
- Low Frequency Generation and Detection of the Lamb Wave A0 Mode Using EMAT
- AMT-PSO : An Adaptive Magnification Transformation Based Particle Swarm Optimizer
- Construction-and-extraction Based Index for Images Retrieval
- Adaptive Bare Bones Particle Swarm Inspired by Cloud Model
- Construction-and-extraction Based Index for Images Retrieval
- Inertial Estimator Learning Automata