The graphical user interface (GUI) to heterogeneous neural network simulators proposed in this article is intended to be of use both for the novice and for the experienced neural network user. For the novice, it provides an easy to use neural network simulation package that insulates the user from the need of knowing the simulator implementation details or the configuration file syntax. For the experienced neural network professional it provides an interface that is easily extensible to include any additional neural network simulator in its binary form. To satisfy both academic and personal computer environments, the GUI has been developed by using the free TCL/TK software package, available both on workstations running UNIX and on PC's running the free Linux operating system. Although the GUI and the embedded simulators have been successfully tested both in neural network research and training programs, a more extensive testing in undergraduate and graduate level classes is in progres...

An algorithm that simultaneously determines an appropriate number of neurons and their interaction parameters in a single hidden layer feed-forward neural network (NN) classification model is proposed. First, a large pool of candidate hidden units with second--order inputs interaction is constructed. Next, the hidden layer is designed by selecting appropriate units from the pool. This is achieved through global hidden layer optimization by a simulated annealing technique that adds and deletes hidden units as needed. Experimental results using the proposed model show improved generalization and reduced complexity as compared to previous constructive learning algorithms based on greedy design techniques. 1. Introduction Determining an appropriate NN topology is a challenging problem that usually requires an expensive trial--and--error process. Rather than learning on a pre--specified network structure, the algorithm proposed in this paper learns network topology as well. The advantage ...