Module-1: Artificial Intelligence

Approaches to AI: Turing Test and Rational Agent Approaches; State Space Representation of Problems, Heuristic Search Techniques, Uninformed search (BFS, DFS, Dijkstra), Informed search (A* search, heuristic functions, hill-climbing), Adversarial search (Game Playing : Minimax algorithm, Alpha-beta pruning) , Local Search, Cutoff Procedures, Constraint Satisfaction Problems: Factor Graphs, Backtracking Search, Dynamic Ordering, Arc consistency.

Knowledge Representation: Logic (Propositional and Predicate Calculus), Semantic Networks, Frames, Rules, Scripts, Conceptual Dependency and Ontologies; Expert Systems, Handling Uncertainty in Knowledge (Quantifying uncertainty, Probabilistic Reasoning, Probabilistic Reasoning over time, Multi‐agent decision making), Probabilistic Reasoning over time: Markov Decision Processes: Policy evaluation, Policy improvement, Policy iteration, Value iteration, Uncertain Reasoning: Probabilistic reasoning, Bayesian Networks (Hidden Markov Models, Kalman Filters, Dynamic Bayesian Networks), Dempster-Shafer theory, Fuzzy logic.

Planning: Components of a Planning System, Linear and Non Linear Planning; Goal Stack Planning, Hierarchical Planning, STRIPS, State space search, Planning Graphs , Partial Order Planning, Automated Planning

Reinforcement Learning: Passive RL, Active RL, Generalization in RL, Policy Search, Deep Reinforcement Learning, Monte Carlo, SARSA, Q‐learning, Exploration/Exploitation, Function approximation, Deep re‐inforcement learning

Natural Language Processing: Rule-based systems, Grammar and Language; Parsing Techniques, Semantic Analysis and Pragmatics.

Multi Agent Systems: Agents and Objects; Agents and Expert Systems; Generic Structure of Multiagent System, Semantic

Web, Agent Communication, Knowledge Sharing using Ontologies, Agent Development Tools.

Fuzzy Sets: Notion of Fuzziness, Membership Functions, Fuzzification and Defuzzification; Operations on Fuzzy Sets, Fuzzy Functions and Linguistic Variables; Fuzzy Relations, Fuzzy Rules and Fuzzy Inference; Fuzzy Control System and Fuzzy Rule Based Systems.

Genetic Algorithms (GA): Encoding Strategies, Genetic Operators, Fitness Functions and GA Cycle; Problem Solving using GA, Evolutionary Computation: Genetic Algorithm, Ant Colony Optimization, Particle Swarm Optimization, Differential Evolution.

Conversational AI, Explainable AI, Understanding AI Ethics and Safety

Reference Books:

• S. Russel and P. Norvig. Artificial Intelligence: A Modern Approach (Third Edition),Prentice Hall, 2009
• E. Rich and K. Knight, Artificial Intelligence, Addison Wesley, 1990
• Yang, Q. (1997), Intelligent Planning: A decomposition and abstraction based approach, Springer Verlag, Berlin Heidelberg
• Sutton and Barto. Reinforcement Learning: An Introduction.

Module-2: Machine Learning

Supervised Learning: 

       Introduction: Motivation, Different types of learning, Linear regression, Simple Linear regression, Multiple  Linear        

regression, Ridge regression, Logistic regression 

       Classifiers: Decision trees, nearest neighbor classifiers, generative classifiers like naive Bayes, linear discriminate 

analysis, Support vector Machines, Linear regression, Logistic regression, bias-variance trade-off

        Gradient Descent: Introduction, Stochastic Gradient Descent, Subgradients, Stochastic Gradient Descent  

for risk minimization

        Support Vector Machines: Hard SVM, Soft SVM, Optimality conditions, Duality, Kernel trick,  Implementing Soft 

SVM with Kernels

        Feature selection techniques: wrapper and filter approaches, back‐ward selection algorithms, forward 

selection algorithms, PCA, LDA

        Decision Trees: Decision Tree algorithms, Random forests

       Cross-Validation Methods: Leave-One-Out (LOO) Cross-Validation, k-folds Cross Validation,

       Neural Networks: Feedforward neural networks, Expressive power of neural networks, Multi-layer  perceptron, 

SGDand Backpropagation

      Model selection and validation: Validation for model selection, k-fold cross-validation, Training-Validation-

Testing split, Regularized loss minimization

Unsupervised Learning and Generative Models:

      Nearest Neighbour: k-nearest neighbour, Curse of dimensionality

      Clustering: Linkage-based clustering algorithms, k-means algorithm, Spectral clustering ,hierarchical, EM, K‐medoid, DB‐Scan, cluster validity indices, similarity measures

      Graphical models: HMM, CRF, MEMM

      Dimensionality reduction: Principal Component Analysis, Random projections, Compressed sensing Generative Models: Maximum likelihood estimator, Naive Bayes, Linear Discriminant Analysis, Latent variables and Expectation-maximization algorithm, Bayesian learning

      Feature Selection and Generation: Feature selection, Feature transformations, Feature learning

      Computational Learning Theory and Deep Neural Networks: 

      Statistical Learning Framework: PAC learning, Agnostic PAC learning, Bias-complexity tradeoff, No free lunch theorem, VC dimension, Structural risk minimization, Adaboost

      Foundations of Deep Learning: DNN, CNN, RNN, Autoencoders

Reference Books:

•  Shalev-Shwartz,S., Ben-David,S., (2014), Understanding Machine Learning: From Theory to Algorithms, Cambridge University Press
• Mitchell Tom (1997). Machine Learning, Tata McGraw-Hill
• Pattern recognition and machine learning by Christopher Bishop, Springer Verlag, 2006
• Kevin P. Murphy. Machine Learning: A Probabilistic Perspective. MIT Press 2012

Module-3: Deep Learning

        Introduction to Deep Learning

       Prerequisite: Linear Algebra, Probability, Numerical Computation, Machine Learning Basics

       Deep Networks: Attention layers, CNN, Gated CNNs, Graph Neural Networks, RNN

       Model Search: Optimization, Regularization, AutoML

       Applications: Practical Methodology and  Neural language models

       Representation Learning & Structured Models

       Linear Factor Models: Autoencoders

      Representation Learning: Unsupervised pre-training, transfer learning and domain adaptation, distributed representation, discovering underlying causes

      Structured Models: Learning about dependencies, Inference and approximate inference, sampling and Monte Carlo Methods, Importance Sampling, Gibbs Sampling, Partition Function, MAP inference and Sparse Coding, Variational Inference

     Deep Generative Models

Deep Generative Models: Deep Belief Networks, Variational Autoencoder, Generative Adversarial Network (GAN), Deep Convolutional GAN, Autoencoder GANs, iGAN, pix2pix, CycleGAN, Conditional GANs, StackGAN

Reference Books:

• Ian Goodfellow, YoshuaBengio and Aaron Courville. Deep Learning. MIT Press 2016
• Yoav Goldberg. 2016. A primer on neural network models for natural language processing. J. Artif. Int. Res. 57, 1 (September 2016), 345‐420.
• R. G. Cowell, A. P. Dawid, S. L. Lauritzen and D. J. Spiegelhalter. "Probabilistic Networks and Expert Systems". Springer‐Verlag. 1999.
• Module-4: Machine Learning Mathematics
•  Overview of supervised and unsupervised learning 
• Undirected graphical models: overview, representation of probability distribution and conditional independence statement, Factorization, CRFs, Applications to NLP, Markov networks.
• Directed graphical models: Bayesian networks.
• Deep Networks for Sequence Prediction: Encoder‐decoder models (case study translation), Attention models, LSTM, Memory Networks
• Deep Network for Generation: Sequence to Sequence Models – VariationalAutoencoders – Generative Adversarial Networks (GANs) – Pointer Generator Networks – Transformer Networks Time series forecasting: models and case‐studies 
• Modern clustering techniques: Multi‐objective optimization for clustering, Deep learning for clustering Online Learning, Mistake Bounds, Sub‐space clustering Meta‐learning and federated learning concepts: tools and techniques Case‐studies: Recent topics for solving various problems of natural language processing, bioinformatics, information retrieval

Reference Books:

• Probability, Random Variables and Stochastic processes by Papoulis and Pillai, 4th Edition, Tata McGraw Hill Edition.
• Linear Algebra and Its Applications by Gilbert Strand. Thompson Books.
• Data Mining: Concepts and Techniques by Jiawei Han, MichelineKamber, Morgan Kaufmann Publishers.
• A. K. Jain and R. C. Dubes. Algorithms for Clustering Data. Prentice Hall, 1988.

Frameworks : (Used for Pyhton Programming)

• Caffe
• Torch7
• Theano
• cuda-convnet
• Ccv
• NuPIC
• DeepLearning4J

Datasets: (Used for Pyhton Programming)

• MNIST Handwritten digits
• Google House Numbers from street view
• CIFAR-10 and CIFAR-100
• IMAGENET
• Tiny Images 
• Flickr dataset and Yahoo dataset
• Berkeley Segmentation Dataset