ABOUT THE COURSE:In this course we will start with traditional Machine Learning approaches, e.g. Bayesian Classification, Multilayer Perceptron etc. and then move to modern Deep Learning architectures like Convolutional Neural Networks, Autoencoders etc. We will learn about the building blocks used in these Deep Learning based solutions. Specifically, we will learn about feedforward neural networks, convolutional neural networks, recurrent neural networks and attention mechanisms. On completion of the course students will acquire the knowledge of applying Machine and Deep Learning techniques to solve various real-life problems.INTENDED AUDIENCE: UG, PG and PhD students and industry professionals who want to work in Machine and Deep Learning.PREREQUISITES: Knowledge of Linear Algebra, Probability and Random Process, PDE will be helpful.INDUSTRY SUPPORT: This is a very important course for industry professionals.
Machine Learning and Deep Learning - Fundamentals and Applications
Indian Institute of Technology Guwahati and NPTEL via Swayam
Overview
Syllabus
Week 1: IntroductionIntroduction to ML, Linear Regression.Week 2: Bayes Decision TheoryBayes Decision Theory, Normal Density and Discriminant Function, Bayes Decision Theory - Binary Features, Bayesian Belief NetworkWeek 3: Parametric and Non- Parametric Density EstimationParametric and Non- Parametric Density Estimation – ML and Bayesian Estimation, Parzen Window and KNNWeek 4: Logistic Regression, Support Vector MachineWeek 5: Random Forest, Hidden Markov ModelDecision trees, Random Forest, Hidden Markov ModelWeek 6: Ensemble methodsEnsemble methods: Ensemble strategies, boosting and bagging.Week 7: Dimensionality ProblemDimensionality Problem, Principal Component Analysis, Linear Discriminant Analysis.Week 8: Gaussian mixture modelConcept of mixture model, Gaussian mixture model, Expectation Maximization AlgorithmWeek 9: ClusteringClustering, k-means, DBSCAN, Hierarchical Agglomerative Clustering, Mean-shift clustering.Week 10: Neural NetworkNeural network: Perceptron, multilayer network, backpropagation, RBF Neural Network, ApplicationsWeek 11: Introduction to deep neural networkIntroduction to deep neural network, Convolutional Neural Networks, AlexNet, VGGNet, GoogLeNet.Week 12: Recent Trends in Deep LearningRecent Trends in Deep Learning Architectures, Transfer Learning Residual Network, Skip Connection Network, Auto encoders and relation to PCA, Recurrent Neural Networks, Applications and Case studies
Taught by
Prof. M. K. Bhuyan
