原文传递
Synaptic Annealing: Anisotropic Simulated Annealing and its Application to Neural Network Synaptic Weight Selection.
| 题名： | Synaptic Annealing: Anisotropic Simulated Annealing and its Application to Neural Network Synaptic Weight Selection. |
| 作者： | Fletcher, J. R. |
| 关键词： | Network science, Neural nets, Notation, Algorithms, Data set, Supervised machine learning, Digital data, Probability, Probability distributions, Random variables, Data mining, Information processing, Quantum tunneling, Computers, Information science, Machine learning, Probabilistic models, Artificial neural networks, Computational science, Simulated annealing, Synaptic annealing, Ffnn(feed-forward neural network), Ann(artificial neural networks) |
| 摘要： | Neural networks are one of the most successful classes of machine learning algorithm, and have been applied to solve problems previously considered to be the exclusive domain of human intellect. Several methods for constructing neural networks exists. This research explores the effectiveness of a feed-forward neural network weight selection procedure called synaptic annealing. Synaptic annealing is the application of the simulated annealing algorithm to the problem of selecting synaptic weights. A novel extension of the simulated annealing algorithm, called anisotropicity, is defined and developed. The cross-validated performance of each synaptic annealing algorithm is evaluated, and compared to back-propagation when trained on several typical machine learning problems. Synaptic annealing is found to be more effective than back-propagation training on classification and regression data sets. These improvements in feed-forward neural network training performance indicate that synaptic annealing may be a viable alternative to back-propagation in many applications of neural networks. |
| 报告类型： | 科技报告 |
相关文献
- DETERIORATION MODELING FOR UNLAID AND OVERLAID PAVEMENTS.
- ARTIFICAL NEURAL NETWORK FOR SELECTING PAVEMENT REHABILITATION PROJECTS
- POCO-MOEA: Using Evolutionary Algorithms to Solve the Controller Placement Problem.
- EXPERT PROJECT RECOMMENDATION PROCEDURE FOR ARIZONA DEPARTMENT OF TRANSPORTATION'S PAVEMENT MANAGEMENT SYSTEM.
- EVOLUTIONARY NEURAL NETWORK MODEL FOR THE SELECTION OF PAVEMENT MAINTENANCE STRATEGY.
- MULTIVARIATE OPTIMIZATION STRATEGIES FOR REAL-TIME TRAFFIC CONTROL SIGNALS.
检索历史
应用推荐
