next up previous contents
Next: Prediction on Diabetes Data Up: Experimental Evaluation Previous: Binary Pattern Recognition

Problems with a Small Input Dimension

Typical application domains for MLPs are data sets with a small input dimension. All the data sets described here represent real world problems, and are obtained from different neural network benchmark databases. Most sets have already been used to investigate the behaviour of BP-trained neural networks by other researchers; some of the results were compared to the findings in these experiments.




next up previous contents
Next: Prediction on Diabetes Data Up: Experimental Evaluation Previous: Binary Pattern Recognition

Albrecht Schmidt
Mit Okt 4 16:45:34 CEST 2000