Add to ORKGAbstract-An extremely simple technique for training the weights of a feedforward multilayer neural network is described and tested. The method, dubbed "neighbor annealing" is a simple random walk through weight space with a gradually decreasing step size. The approach is compared against backpropagation and particle swarm optimization on a variety of training tasks. Neighbor annealing is shown to perform as well or better on the test suite, and is also shown to have pragmatic advantages
In this paper we proposed a novel procedure for training a feedforward neural network. The accuracy ...
This paper investigates neural network training as a potential source of problems for benchmarking c...
Artificial neural networks have, in recent years, been very successfully applied in a wide range of ...
The training of multilayer perceptron is generally a difficult task. Excessive training times and la...
We show how a feed-forward neural network can be sucessfully trained by using a simulated annealing ...
Simulated Annealing is a meta-heuristic that performs a randomized local search to reach near-optima...
This work introduces an alternative algorithm, simulated annealing, to minimize the prediction error...
In recent years neuroevolution has become a dynamic and rapidly growing research field. Interest in ...
In this dissertation the problem of the training of feedforward artificial neural networks and its a...
Abstract—We develop, in this brief, a new constructive learning algorithm for feedforward neural net...
In this work, we propose a Hybrid particle swarm optimization-Simulated annealing algorithm and pres...
Multilayer feed-forward artificial neural networks are one of the most frequently used data mining m...
The over-parameterization of neural networks and the local optimality of backpropagation algorithm h...
Machine learning algorithms have become a ubiquitous, indispensable part of modern life. Neural netw...
In this paper, we propose a hybrid learning algorithm for the single hidden layer feedforward neural...
In this paper we proposed a novel procedure for training a feedforward neural network. The accuracy ...
This paper investigates neural network training as a potential source of problems for benchmarking c...
Artificial neural networks have, in recent years, been very successfully applied in a wide range of ...
The training of multilayer perceptron is generally a difficult task. Excessive training times and la...
We show how a feed-forward neural network can be sucessfully trained by using a simulated annealing ...
Simulated Annealing is a meta-heuristic that performs a randomized local search to reach near-optima...
This work introduces an alternative algorithm, simulated annealing, to minimize the prediction error...
In recent years neuroevolution has become a dynamic and rapidly growing research field. Interest in ...
In this dissertation the problem of the training of feedforward artificial neural networks and its a...
Abstract—We develop, in this brief, a new constructive learning algorithm for feedforward neural net...
In this work, we propose a Hybrid particle swarm optimization-Simulated annealing algorithm and pres...
Multilayer feed-forward artificial neural networks are one of the most frequently used data mining m...
The over-parameterization of neural networks and the local optimality of backpropagation algorithm h...
Machine learning algorithms have become a ubiquitous, indispensable part of modern life. Neural netw...
In this paper, we propose a hybrid learning algorithm for the single hidden layer feedforward neural...
In this paper we proposed a novel procedure for training a feedforward neural network. The accuracy ...
This paper investigates neural network training as a potential source of problems for benchmarking c...
Artificial neural networks have, in recent years, been very successfully applied in a wide range of ...