Course

Unit I

Deep Learning Architectures, Machine Learning and Deep Learning, Representation Learning, Width and Depth of Neural Networks, Activation Functions: RELU, LRELU, ERELU, Unsupervised Training of Neural Networks, Back Propagation Learning Algorithm, binary and multiclass classification using neural networks, self-organizing maps, Restricted Boltzmann Machines, Auto Encoders, Deep Learning Applications

Unit II

Convolutional Neural Networks, Architectural Overview, Motivation, Convolutional Layers, Filters, Parameter sharing, Regularization Methods, optimization techniques used in Deep Learning (Gradient Descent, Stochastic-GD, Batch-SGD, Momentum, NAG, Adagrad, Adadelta, RMSprop, and Adam), Popular CNN Architectures: ResNet, AlexNet – Applications of image processing

Unit III

Transfer Learning, Transfer learning Techniques, Variants of CNN: DenseNet, PixelNet, ImageNet. Applications of using these learning techniques.

Unit IV

Auto Encoders, Under complete Autoencoder, Regularized Autoencoder, stochastic Encoders, and Decoders, Contractive Encoders – generative adversarial network (GAN).

Unit V

Sequence Modelling – Recurrent And Recursive Nets, Recurrent Neural Networks, Bidirectional RNNs, Encoder-decoder sequence to sequence Architectures – BPTT for training RNN, Long Short Term Memory Networks, Case Studies: Deep Learning for any sequential or time series data applications

Course Outcomes

1. To understand the theoretical foundations, algorithms, and methodologies of Neural Network
2. To design and develop an application using specific deep-learning models
3. To provide practical knowledge in handling and analyzingreal-world applications
4. To select and use the appropriate Optimization techniques for deep learning models

CO PO Mapping:

Text Books/ Reference Books:

1. Ian Goodfellow, YoshuaBengio and Aaron Courville, “ Deep Learning”, MIT Press, 2017.
2. Josh Patterson, Adam Gibson “Deep Learning: A Practitioner’s Approach”, O’Reilly Media, 2017
3. Umberto Michelucci “Applied Deep Learning. A Case-based Approach to Understanding Deep Neural Networks” Apress, 2018.
4. Kevin P. Murphy “Machine Learning: A Probabilistic Perspective”, The MIT Press, 2012.
5. EthemAlpaydin,”Introduction to Machine Learning”, MIT Press, Prentice Hall of India, ThirdEdition 2014.
6. Giancarlo Zaccone, Md. RezaulKarim, Ahmed Menshawy “Deep Learning with TensorFlow:Explore neural networks with Python”, Packt Publisher, 2017.
7. Antonio Gulli, Sujit Pal “Deep Learning with Keras”, Packt Publishers, 2017.
8. Francois Chollet “Deep Learning with Python”, Manning Publications, 2017.