Unit I Fundamentals of Deep Learning What is Deep Learning?, Multilayer Perceptron ,Feed forward neural, Back propagation, Gradient descent, Vanishing gradient problem, Activation Functions : RELU, LRELU, ERELU, Optimization Algorithms, Hyper parameters : Layer size, Magnitude (momentum, learning rate),Regularization (dropout, drop connect, L1, L2) (Chapter - 1) Unit II Convolutional Neural Network Introduction to CNN, Convolution Operation, Parameter Sharing, Equivariant Representation, Pooling, Variants of the Basic Convolution Function, The basic Architecture of CNN, Popular CNN Architecture – AlexNet. (Chapter - 2) Unit III Recurrent Neural Networks Recurrent Neural Networks: Types of Recurrent Neural Networks, Feed-Forward Neural Networks vs Recurrent Neural Networks, Long Short-Term Memory Networks (LSTM), Encoder Decoder architectures, Recursive Neural Networks. (Chapter - 3) Unit IV Autoencoders Undercomplete Autoencoders, Regulraized Autoencoders-Sparse Autoencoders, Stochastic Encoders and Decoders, Denoising Autoencoders, Contractive Autoencoders, Applications of Autoencoders. (Chapter - 4) Unit V Representation Learning Greedy Layerwise Pre-training, Transfer Learning and Domain Adaption, Distributed Representation, Variants of CNN: DenseNet. (Chapter - 5) Unit VI Applications of Deep Learning Overview of Deep Learning Applications : Image Classification, Social N/w/ analysis, Speech Recognition, Recommender system, Natural Language Processing. (Chapter - 6)
