NNDT - A Neural Network Development Tool

A tool for analysis, modelling, simulation and prediction with feedforward and recurrent neural networks is presented. The Neural Network Development Tool (NNDT) is implemented in Visual Basic and C and runs under MS Windows on personal computers. Network training is carried out by the Levenberg-Marquardt method and the user interface facilitates interactive analysis and modification of parameters as well as illustration of results. The features offered by the tool are especially useful in the difficult process of training recurrent networks, but are also of value, e.g., in scanning the performance of feedforward networks for analysing if and when overfitting occurs.

[1]  Abhay B. Bulsari,et al.  A Recurrent Neural Network for Time-series Modelling , 1993 .

[2]  Abhay B. Bulsari,et al.  A recurrent network for modeling noisy temporal sequences , 1995, Neurocomputing.

[3]  David E. Rumelhart,et al.  Predicting the Future: a Connectionist Approach , 1990, Int. J. Neural Syst..

[4]  Ferdinand Hergert,et al.  Improving model selection by nonconvergent methods , 1993, Neural Networks.

[5]  Howell Tong,et al.  Non-Linear Time Series , 1990 .

[6]  William H. Press,et al.  Numerical recipes , 1990 .

[7]  Ronald J. Williams,et al.  A Learning Algorithm for Continually Running Fully Recurrent Neural Networks , 1989, Neural Computation.

[8]  L. Ljung,et al.  A system identification perspective on neural nets , 1992, Neural Networks for Signal Processing II Proceedings of the 1992 IEEE Workshop.