Difference between Training set, Validation set and Test Set

Training set: A set of examples used for learning, which is to fit the parameters [i.e., weights] of the classifier.

Validation set: A set of examples used to tune the parameters [i.e., architecture, not weights] of a classifier, for example to choose the number of hidden units in a neural network. Validation set could be used to find the parameters that controls complexity of neural networks structure or other machine learning models.

Test set: A set of examples used only to assess the performance [generalization] of a fully specified classifier.