Here is a regression example: tools/demos/regression/uci-isolet/isolet.conf
To train it, you have to:
The dataset is a spoken letter recognition dataset with 6238 training sample. It contains 26 categories and its inputs have 617 components.
While this dataset should be trained in classification mode, we use it here just to demonstrate how to train for regression.
Hence the obtained results are poor: the 'test_errors' should converge to approximately 62% error after 50 iterations.
To train on this dataset in classification mode, simply uncomment the last section of isolet.conf ('classification' section) and call