A Study On Hill Climbing Algorithms For Neural Network Training
نویسندگان
چکیده
This study empirically investigates variations of hill climbing algorithms for training artiicial neural networks on the 5-bit parity classiication task. The experiments compare the algorithms when they use diierent combinations of random number distributions, variations in the step size and changes of the neural net-works' initial weight distribution. A hill climbing algorithm which uses inline search is proposed. In most experiments on the 5-bit parity task it performed better than simulated annealing and standard hill climbing.
منابع مشابه
Comparison 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 کاملDesign Issues In Hill CliIllbing For Neural Network Training
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 tra...
متن کاملArtifi cial Neural Network based Maximum Powerpoint Tracking of Solar Panel
Maximum Power Point Tracking (MPPT) is necessary for Solar Photo Voltaic (SPV) system. Many algorithms such as Perturb and Observe, Incremental conductance and hill climbing are available to track the maximum power. But they have disadvantages such as high cost, diffi cult to implement and instable. Artifi cial Neural Network (ANN) is suitable for handling non-linearites, uncertainties and para...
متن کاملAutomating Vehicles by Deep Reinforcement Learning using Task Separation with Hill Climbing
Within the context of autonomous vehicles, classical model-based control methods suffer from the trade-off between model complexity and computational burden required for the online solution of expensive optimization or search problems at every short sampling time. These methods include samplingbased algorithms, lattice-based algorithms and algorithms based on model predictive control (MPC). Rec...
متن کاملA Learning Automata Based Algorithm for Determination of the Number of Hidden Units for Three Layers Neural Networks
There is no method to determine the optimal topology for multi-layer neural networks for a given problem. Usually the designer selects a topology for the network and then trains it. Since determination of the optimal topology of neural networks belongs to class of NP-hard problems, most of the existing algorithms for determination of the topology are approximate. These algorithms could be class...
متن کامل