National Institute of Technology Rourkela

राष्ट्रीय प्रौद्योगिकी संस्थान राउरकेला

ଜାତୀୟ ପ୍ରଯୁକ୍ତି ପ୍ରତିଷ୍ଠାନ ରାଉରକେଲା

An Institute of National Importance

Syllabus

Course Details

Subject {L-T-P / C} : CS6510 : Deep Learning { 3-0-0 / 3}

Subject Nature : Theory

Coordinator : Puneet Kumar Jain

Syllabus

Module 1 :

UNIT – I
Basics related to Calculus, Linear Algebra, Python 3, probability and optimization.

UNIT – II
Gradient descent, cost function, Stochastic gradient descent, Adam, Momentum, Neural Networks, Deep Neural Networks, hyperparameter tuning, Regularization.

UNIT – III
Basics of CNNs. Detailed understanding of LeNet and Alexnet Architectures, ResNet, VGG-16, VGG-19. Their implementations.

UNIT – IV
Basics of RNNs. Detailed understanding of sequence models, text generation, neural machine translation, and speech.

Course Objective

1 .

Understand the fundamentals of feedforward, recurrent and convolutional neural networks and apply them to solve various real-world problems.

2 .

Develop a deeper understanding in different optimization algorithms gradient descent, stochastic gradient descent and recent developments like ADAM and RMSprop.

3 .

Explore state-of-the-art architectures (CNN, LSTM, GRU, Bidirectional Models and Deep Generative Models) and learn transfer learning with feature and decision level fusion.

4 .

Learn to improve the computational efficiency and performance of DL models for a specific problem by optimizing hyperparameters and employing GPUs

Course Outcome

1 .

1. Develop in depth understanding of the key deep learning models and concepts.
2. Gain practical skills and theoretical knowledge necessary to apply deep learning techniques to a wide range of problems.
3. Improve the performance (tuning hyperparameters) and computational efficiency (using GPUs) of deep learning models for real-world problems.
4. Determining an appropriate deep learning model for an application.

Essential Reading

1 .

A. Zhang, Z.C. Lipton, M. Li, A.J. Smola, Dive into Deep Learning, Cambridge University Press , Website: https://d2l.ai

2 .

Ian Goodfellow, Yoshua Bengio, Aaron Courville, Deep Learning, MIT Press , Website: https://www.deeplearningbook.org/

Supplementary Reading

1 .

Francois Chollet, Deep Learning with Python, Manning Publishers

2 .

E. Stevens, L. Antiga, T. Viehmann, Deep Learning with PyTorch, Manning Publishers

Journal and Conferences

1 .

IEEE Transactions on Pattern Analysis and Machine Intelligence

2 .

AAAI Conference on Artificial Intelligence