M.Sc. (Information Technology) Deep Learning Syllabus - Mumbai University

• a Applied Math and Machine Learning Basics: Linear Algebra: Scalars, Vectors, Matrices and Tensors, Multiplying Matrices and Vectors , Identity and Inverse Matrices, Linear Dependence and Span , norms, special matrices and vectors, Eigen decompositions.
• b Numerical Computation: Overflow and under flow, poor conditioning, Gradient Based Optimization, Constraint optimization.

• a Deep Networks: Deep feed forward network, regularization for deep learning, Optimization for Training deep models.

• a Convolution Applications: Convolutional Networks, Sequence Modelling, Applications
• b Deep Learning Research: Linear Factor Models, Auto encoders, representation learning

• a Generative Models: Approximate Inference, Deep Generative Models
• b Diff usion Models (Reference 3)
• c Applications: Transformers, Advance GANs (Reference 3) After completion of the course, a student will be able to: CO1: Describe basics of mathematical foundation that will help the learner to understand the Concepts of Deep Learning. CO2: Understand and describe model of deep learning CO3: Understand various deep supervised learning architectures for text & image data. CO4: Gain knowledge about various deep learning models and architectures. CO5: Familiarize various deep learning techniques to design efficient algorithms for real- world applications.

Books and References

• 1 Deep Learning Ian Yoshua Bengio, An MIT Press 1st 2016 Goodfellow, Aaron book
• 2 Fundamentals of Deep Nikhil Buduma O’Reilly 1st 2017 Learning
• 3 Generative Deep Learning David Foster O’Reilly 2nd 2023
• 4 Deep Learning: Methods and Deng & Yu Now Publishers 1st 2013 Applications
• 5 Deep Learning CookBook Douwe Osinga O’Reilly 1st 2017