Course

Unit 1

The Neuron – Feed-Forward Neural Networks – Linear neurons and their limitations Activation functions – Training feed forward neural networks – Gradient descent – Delta rule and learning rates – Backpropagation algorithm – Stochastic and minibatch gradient descent – Preventing overfitting – Momentum-Based optimization-Learning rate adaptation.??

Unit 2

Convolutional Neural Networks (CNN) architecture – Accelerating training with batch normalization – Visualizing learning in convolutional networks – Embedding and representation learning – Autoencoder architecture – Denoising – Sparsity in autoencoders.??

Unit 3

Models for sequence analysis, Recurrent Neural Networks – Vanishing gradients – Long Short – Term Memory (LSTM) Units – Augmenting Recurrent networks with Attention – Deep Generative Networks – Generative Adversarial Networks.

Prerequisite(s): Machine Learning

Objectives:?

• To introduce artificial neural networks and their architecture?
• To introduce techniques used for training artificial neural networks?
• To enable design of deep learning models for classification and sequence analysis

?Course Outcomes?

• CO1: Able to understand different types of neural network architectures and their working.?
• CO2: Able to understand the mathematics behind artificial neural networks.?
• CO3: Able to design neural networks for classification and sequence detection?
• CO4: Able to implement deep learning models for classification and sequence detection type applications?

?CO – PO Mapping?

Text Book(s)  

1. M, Deep Learning, First Ed., Delhi: Pearson Education, 2022.
2. G. Amlan Chakrabarti Amit Kumar Das, Deep Learning, First Edition. Pearson Education, 2021.

 Reference(s): 

1. Ian Goodfellow, Yoshua Bengio, Aaron Courville, Deep Learning, MIT Press;
2. Nithin Buduma, Nikhil Buduma, Joe Papa, Fundamentals of Deep Learning: Designing Next-Generation Machine Intelligence Algorithms, 2^nd Edition,(Grayscale Indian Edition), O’Reilly Media;  
3. Charu C. Aggarwal, Neural Networks and Deep Learning-A Textbook, Springer Cham;