Distribution of the search of evolutionary product unit neural networks for classification
This work addresses efficiency challenges in neural network design for researchers using evolutionary algorithms, but it appears incremental as it focuses on distributed processing without claiming major breakthroughs.
The paper tackles the high computational cost of training evolutionary product unit neural networks for classification by implementing a distributed search across a computer cluster, aiming to achieve more efficient designs than non-distributed methods.
This paper deals with the distributed processing in the search for an optimum classification model using evolutionary product unit neural networks. For this distributed search we used a cluster of computers. Our objective is to obtain a more efficient design than those net architectures which do not use a distributed process and which thus result in simpler designs. In order to get the best classification models we use evolutionary algorithms to train and design neural networks, which require a very time consuming computation. The reasons behind the need for this distribution are various. It is complicated to train this type of nets because of the difficulty entailed in determining their architecture due to the complex error surface. On the other hand, the use of evolutionary algorithms involves running a great number of tests with different seeds and parameters, thus resulting in a high computational cost