Design Issues In Hill CliIllbing For Neural Network Training
نویسندگان
چکیده
Hill climbing algorithms can train neural control systems for adaptive agents. They are an alternative to gradient descent algorithms especially if neural networks with non-layered topology or non-differentiable activation function are used, or if the task is not suitable for backpropagation training. This paper describes three variants of generic hill climbing algorithms which together can train nearly any type of neural network. Variations of the algorithms are analysed and tested on the 5-bit parity data .and practical design rules are inferred. A hill climbing algorithm which uses inline search is proposed. Experimental results show that it can accelerate learning. It can be recommended for' population based training.
منابع مشابه
EVALUATION OF CONCRETE COMPRESSIVE STRENGTH USING ARTIFICIAL NEURAL NETWORK AND MULTIPLE LINEAR REGRESSION MODELS
In the present study, two different data-driven models, artificial neural network (ANN) and multiple linear regression (MLR) models, have been developed to predict the 28 days compressive strength of concrete. Seven different parameters namely 3/4 mm sand, 3/8 mm sand, cement content, gravel, maximums size of aggregate, fineness modulus, and water-cement ratio were considered as input variables...
متن کاملComparison of Genetic and Hill Climbing Algorithms to Improve an Artificial Neural Networks Model for Water Consumption Prediction
No unique method has been so far specified for determining the number of neurons in hidden layers of Multi-Layer Perceptron (MLP) neural networks used for prediction. The present research is intended to optimize the number of neurons using two meta-heuristic procedures namely genetic and hill climbing algorithms. The data used in the present research for prediction are consumption data of water...
متن کاملReliability-Based Robust Multi-Objective Optimization of Friction Stir Welding Lap Joint AA1100 Plates
The current paper presents a robust optimum design of friction stir welding (FSW) lap joint AA1100 aluminum alloy sheets using Monte Carlo simulation, NSGA-II and neural network. First, to find the relation between the inputs and outputs a perceptron neural network model was obtained. In this way, results of thirty friction stir welding tests are used for training and testing the neural network...
متن کاملGlobal Solar Radiation Prediction for Makurdi, Nigeria Using Feed Forward Backward Propagation Neural Network
The optimum design of solar energy systems strongly depends on the accuracy of solar radiation data. However, the availability of accurate solar radiation data is undermined by the high cost of measuring equipment or non-functional ones. This study developed a feed-forward backpropagation artificial neural network model for prediction of global solar radiation in Makurdi, Nigeria (7.7322 N lo...
متن کاملA conjugate gradient based method for Decision Neural Network training
Decision Neural Network is a new approach for solving multi-objective decision-making problems based on artificial neural networks. Using inaccurate evaluation data, network training has improved and the number of educational data sets has decreased. The available training method is based on the gradient decent method (BP). One of its limitations is related to its convergence speed. Therefore,...
متن کامل