Theano in Action to implement Deep Learning Algorithm

Deep Learning Framework: 1.Deep Convolutional Network 2.Deep Belief Networks(Restricted Boltzmann Machines) - unsupervised generative pre-training of stacked RBMs followed by supervised fine-tuning 3.Auto Encoders, Denoising Autoencoders - description of autoencoders 4.Stacked Denoising Auto-Encoders - easy steps into unsupervised pre-training for deep nets

Others: 1.HMC Sampling - hybrid Monte Carlo Sampling with scan() 2.Contrative auto-encoders 3.Semantic Parsing of Speech using Recurrent Net 4.LSTM network for sentiment analysis