Back close

Course Detail

Course Name Deep Learning
Course Code 26CSC304
Program 5 Year Integrated M.Sc in Data Science
Semester 5
Credits 4
Campus Coimbatiore

Syllabus

Syllabus

Basics: Biological Neuron, Idea of computational units, McCulloch–Pitts unit and Thresholding logic, Linear Perceptron, Perceptron Learning Algorithm, Linear separability. Convergence theorem for Perceptron Learning Algorithm.

Feedforward Networks: Multilayer Perceptron, Gradient Descent, Backpropagation, Empirical Risk Minimization, regularization, autoencoders.

Deep Neural Networks: Difficulty of training deep neural networks, Greedy layerwise training.

Better Training of Neural Networks: Newer optimization methods for neural networks (Adagrad, adadelta, rmsprop, adam, NAG), second order methods for training, Saddle point problem in neural networks, Regularization methods (dropout, drop connect, batch normalization).

Convolutional Neural Networks: LeNet, AlexNet.

Recurrent Neural Networks: Back propagation through time, Long Short Term Memory, Gated Recurrent Units, Bidirectional LSTMs, Bidirectional RNNs

Generative models: Restrictive Boltzmann Machines (RBMs), Introduction to MCMC and Gibbs Sampling, gradient computations in RBMs, Deep Boltzmann Machines.

Recent trends: Variational Autoencoders, Generative Adversarial Networks, Multi-task Deep Learning, Multi-view Deep Learning.

Transformers: Transfer learning, data augmentation and hyperparameter search.

Applications: Vision, NLP, Speech (just an overview of different applications in 2-3 lectures)

Case Studies with Keras, MXNet, Deeplearning4j, Tensorflow, CNTK, or Theano

Text Books / References

Textbook:

  1. Deep Learning, Ian Goodfellow and Yoshua Bengio and Aaron Courville, MIT Press, 2016.

References:

  1. Ian Goodfellow, YoshuaBengio and Aaron Courville, Deep Learning, MIT press 2016
  2. Neural Networks: A Systematic Introduction, Raúl Rojas, 1996
  3. Pattern Recognition and Machine Learning, Christopher Bishop, 2007

Objectives and Outcomes

Course Outcomes (COs):

Course Outcomes
CO1 To understand the theoretical foundations, algorithms, and methodologies of Neural Networks.
CO2 To design, implement, and evaluate deep learning models for real-world applications.
CO3 To analyze model performance and apply appropriate optimization and regularization techniques.
CO4 To explore modern deep learning architectures including CNNs, RNNs, Transformers, and Generative Models.
CO5 To explore sequence modlling algorithms are BPTT, LSTM, GRU and application in NLP.

CO-PO Mapping:

  PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12
CO1 3 3 2 2 2 2         3 1
CO2 3 2 2 2 2 2         3 1
CO3 3 2 2 2 2 3         3 1
CO4 3 2 1 2 2 2         3 1
CO5 3 2 2 2 2 2         3 1

DISCLAIMER: The appearance of external links on this web site does not constitute endorsement by the School of Biotechnology/Amrita Vishwa Vidyapeetham or the information, products or services contained therein. For other than authorized activities, the Amrita Vishwa Vidyapeetham does not exercise any editorial control over the information you may find at these locations. These links are provided consistent with the stated purpose of this web site.

Admissions Apply Now