---------------------------------------------------

Some examples to learn how to *program* in Torch3.
Of course you can use them without any changes,
but you will not use 1/10 of the library if you
don't want to code something!

boosting.cc:  adaboost with MLP in classification.
knn.cc:       K-nearest-neighbors algorithm.
mlp.cc:       multi-layered perceptron.
svm.cc:       support vector machines.
svm_multi.cc: SVM with more than two classes.

---------------------------------------------------

You will find two examples of datasets in data/.
Torch3 is able to deal directly with gziped data,
but you can uncompress them if you want to have a
look. (Or do a zless, zcat, zmore).

These data are classification data: there is 784
inputs (the first 784 columns) and the 1 target
which can take values between 0..9. (10 classes).

---------------------------------------------------

Examples of command line:

Linux_OPT_FLOAT/boosting -nhu 5 ", &m                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                       