Matlab/Octave toolbox for deep learning. Includes Deep Belief Nets, Stacked Autoencoders, Convolutional Neural Nets, Convolutional Autoencoders and vanilla Neural Nets. Each method has examples to get you started.
Look into nnpredict(), basically after nnff() the nn.a{end} is the probabilities (softmax layer activations). nnpredict() just picks the class with highest probability.
For the classification in nntest after training, this toolbox can not return the probability of the classification results, right??