Classification by Ensembles of Neural Networks
This is an incremental approach to neural network training for classification tasks, with no specific problem or audience mentioned.
The paper tackles the problem of training neural networks for classification by proposing a new procedure that approximates the objective function using the arithmetic mean of an ensemble of randomly generated networks, differing from standard optimization-based methods.
We introduce a new procedure for training of artificial neural networks by using the approximation of an objective function by arithmetic mean of an ensemble of selected randomly generated neural networks, and apply this procedure to the classification (or pattern recognition) problem. This approach differs from the standard one based on the optimization theory. In particular, any neural network from the mentioned ensemble may not be an approximation of the objective function.