Course Code: DA323	Course Name: Multi-modal Data Processing and Learning - II	Credits: 3-0-0-6
Pre-requisite: None
Syllabus: Multi-modal data synchronization and fusion: Data understanding and quality estimation, meta data filtering, amount of data estimation for multimodal design, data synchronization and fusion, imbalance data analysis for multimodal design. Multi-modal learning and associated challenges: Applications and challenges from fusing two or more modalities such as vision, language, audio, graphs, biomedical signals; Development of shallow and deep networks for multimodal learning. Multi-modal processing and learning with applications: Image captioning, visual questioning answering system, automatic commentary generation, cognitive state estimation, recommendation system.
Textbooks: A But, A Miasnikov, G Ortolani, Multimodal Deep Learning with Tensorflow: Translate mathematics into robust TensorFlow applications with Python, Packt Publishing Limited, 2019. M Yang, B Rosenhahn, V Murino, Multimodal Scene Understanding: Algorithms, Applications and Deep Learning, Academic Press Inc, 2019. J-P Thiran, F Marqués and H Bourlard, Multimodal Signal Processing: Theory and applications for human-computer interaction, Academic Press, 2009.
References: T. Baltrušaitis, C. Ahuja and L. Morency, Multimodal Machine Learning: A Survey and Taxonomy in IEEE Transactions on Pattern Analysis and Machine Intelligence, 41(2), 423-443, 2019. Y. Bengio, A. Courville, P. Vincent, Representation Learning: A Review and New Perspectives, IEEE Transactions on Pattern Analysis and Machine Intelligence,35(8),1798-1828, 2013.

Course Code: DA324	Course Name: Data Mining	Credits: 3-0-0-6
Pre-requisite: None
Syllabus: Introduction: Definition, Recap of Basics of Data Analysis; Introduction to Data warehousing; Finding Similar Items: Similarity search methods, KNN, Shingling, Locality sensitive hashing; Frequent Pattern Mining: Itemset mining, Substring mining, Sequence mining, Pattern assessment; Graph Mining: Link Analysis, Graph pattern mining, Mining Social-Network Graph, Graph clustering; Mining Data Streams.
Textbooks: Mohammed J. Zaki and Wagner Meira, Jr, Data Mining and Machine Learning: Fundamental Concepts and Algorithms, 2nd Edition, Cambridge University Press, 2020. Jure Leskovec, Anand Rajaraman and Jeffrey David Ullman, Mining of Massive Datasets, 3rd Edition, Cambridge University Press, 2020.
References: Pang-Ning Tan, Michael Steinbach, and Vipin Kumar, Introduction to Data Mining, 2nd Edition, Pearson Publication, 2018.

Course Code: DA325	Course Name: Deep Learning	Credits: 3-0-0-6
Pre-requisite: None
Syllabus: Introduction to Deep Learning and its Applications, Computational Graph; Convolutional Neural Networks: Convolution, pooling, Activation Functions, Back propagation of CNN, Weights as templates, Translation invariance, Training with shared parameters; CNN Architecture Design and Discussion: AlexNet, VGG, GoogLeNet, ResNet, Deep vs Shallow Networks, Transfer Learning and Its types; Loss Functions and Optimization: Optimization, stochastic gradient descent, dropout, batch normalization; Sequential Modelling: Recurrent and Recursive Nets, RNN, LSTM, GRU; Visualization and Understanding: Visualizing intermediate features and outputs, Saliency maps, Visualizing neurons; Generative Models: Auto encoders, Generative Adversarial Networks; Deep Learning Applications: Conventional and Aerial view; Adversarial Attacks on CNN; Recent trends in deep learning.
Textbooks: Ian Goodfellow, Yoshua Bengio and Aaron Courville, Deep Learning, MIT Press, 2016. Michael A. Nielsen, Neural Networks and Deep Learning, Determination Press, 2015.
References: Yoshua Bengio, Learning Deep Architectures for AI, Now Publishers Inc., 2009.

Course Code: DA352	Course Name: Privacy and Information Security	Credits: 3-0-0-6
Pre-requisite: None
Syllabus: Overview: vulnerabilities, risk assessment, incidents; Basic terminology: Confidentiality, integrity, availability, non-repudiation, authentication, access control, passive and active attacker, interception, modification, fabrication, social engineering; Cryptography basics: Classical cryptography, block ciphers, symmetric cryptography, hash function, public key, digital signatures; System security: Exploiting bugs in programs. Buffer overflows, fuzzing, Certification, secure socket layer (SSL), Kerberos, SQL injection, concepts of vulnerability, risk management, worm, virus, malware, anti-viruses; Network security: Host IDS, network IDS, firewall, ARP poisoning, IP spoofing, DoS attacks; Data Privacy: Mathematical definitions of privacy, attacks on privacy and anonymity, social media privacy K-anonymity, Differential privacy, Private information retrieval, basics of multiparty computation and relationship to privacy; Mobile Application Security.
Textbooks: William Stallings, Network Security Essentials (Applications and Standards), 6th Edition, Pearson, 2018.
References: Ross J. Anderson, Security Engineering, 3rd Edition, Wiley, Nov 2020. Anco Hundepool, Statistical Disclosure Control, 1st Edition, Wiley, 2012. Nataraj Venkataramanan and Ashwin Shriram, Data Privacy: Principles and Practice, 1st Edition, Taylor Francis, 2016. George T. Duncan, et al., Statistical Confidentiality: Principle and Practice, Springer, 2011. Cynthia Dwork and Aaron Roth, The Algorithmic Foundations of Differential Privacy, Found. Trends Theor. Comput. Sci. 9, 2014.

Course Code: DA312	Course Name: Advanced Machine Learning Laboratory	Credits: 0-0-3-3
Pre-requisite: None
Syllabus: Familiarization with TensorFlow/PyTorch; Implementation of MLP: Training Issues with Deep Networks, Applications; Autoencoders: Practical Applications; CNN: Constructing small networks to classify MNIST/CIFAR10, training issues; CNN: Realizing popular architectures, experiments with ImageNet scale data; Object/Face detection and localization; RNN and LSTM: training on sequences; Application in NLP: sentence representation using LSTM; Multimodal applications: vision and language.
Textbooks: Zhang, Aston, Zachary C. Lipton, Mu Li, and Alexander J. Smola, Dive into deep learning, 2021. Ian Goodfellow, Yoshua Bengio and Aaron Courville, Deep Learning, MIT Press, 2016. Michael A. Nielsen, Neural Networks and Deep Learning, Determination Press, 2015.
References: C. M. Bishop, Pattern Recognition and Machine Learning (Information Science and Statistics), 2nd Edition, Springer, 2011. S. O. Haykin, Neural Networks and Learning Machines, 3rd Edition, Pearson Education (India), 2016.

Course Code: DA353	Course Name: Internet of Things	Credits: 2-0-2-6
Pre-requisite: None
Syllabus: Internet of Things (IoT) and its evolution; IoT layered architecture and devices: Sensors, microcontroller and connectivity, communication types and technologies: Short, mid and long-range communication; IoT messaging protocols: MQTT, CoAP, AMQP and HTTP; Overview of edge computing and cloud computing for IoT; IoT Security, IoT application examples, Artificial Intelligence (AI)-enabled IoT for real-world applications.
Textbooks: Simone Cirani, Gianluigi Ferrari, Marco Picone and Luca Veltri, Internet of Things Architectures, Protocols and Standards, 1st Edition, John Wiley & Sons Ltd, 2019. David Hanes, Gonzalo Salgueiro, Patrick Grossetete, Robert Barton, Jerome Henry, IoT Fundamentals: Networking Technologies, Protocols, and Use Cases for the Internet of Things, 1st Edition, Pearson India Pvt. Ltd, 2018. Peter Marwedel, Embedded system design: embedded systems foundations of cyber-physical systems, and the internet of things, 1st Edition, Springer Nature, 2021.
References: Pallavi Sethi and Smruti R. Sarangi, Internet of Things: Architectures, Protocols, and Applications, Hindawi Journal of Electrical and Computer Engineering, 2017. Qusay F Hassan, Internet of things A to Z: technologies and applications, 1st Edition, John Wiley & Sons, 2018. Arshdeep Bahga and Vijay Madisetti, Internet of Things: A Hands-on Approach, 1st Edition, Universities Press (India) Pvt. Ltd., 2015.

Course Code: DA332	Course Name: Data Visualization	Credits: 1-0-3-5
Pre-requisite: None
Syllabus: Introduction to data visualization: Definition, Various forms of data visualization; Grammar of graphics: Designing graphs or plots layer-by-layer; Grouping and Faceting; Design Principles; Different chart families: Category, Hierarchical, Relation, Temporal and Spatial (CHRTS); Real time data visualization. Lab assignments and mini projects will be given as per the theory discussed in lectures.
Textbooks: K Healy, Data Visualization: A Practical Introduction, 1st Edition, Princeton University Press, 2019. Claus Wilke, Fundamentals of Data Visualization: A primer on making informative and compelling figures, 1st Edition, O’Reilly Publications, 2019.
References: A Kirk, Data Visualization: A Handbook for Data Driven Design, 2nd Edition, 2019. L Wilkinson, The Grammar of Graphics, 2nd Edition, Springer, 2013.