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} : EC6604 : Machine Intelligence { 3-0-0 / 3}

Subject Nature : Theory

Coordinator : Samit Ari

Syllabus

Module 1 :

Module-1: [7 Hours]
Introduction to Machine Learning: Types of machine learning, Supervised learning, Unsupervised learning, basic concepts in machine learning, K-Nearest Neighbours Algorithm.

Module-2: [12 Hours]
Bayesian Decision Theory: A brief review of probability theory, Bayes rule, Bayesian concept learning, Likelihood, Prior, Posterior, Minimum Risk Classifier, Multivariate Normal Density Function, Discriminant Function, Binary Features, Linear Models of Regression: linear basis function models, Maximum likelihood estimation, Mixture Models and EM algorithm: Mixtures of Gaussians, GMM, EM algorithm.

Module-3: [5 Hours]
Component Analysis and Discriminants: Dimensionality Reduction, Subset Selection, Principal Component Analysis (PCA), linear discriminant analysis (LDA).

Module-4: [8 Hours]
Different Learning Techniques: Fundamentals of Neural Network, Support Vector Machine (SVM): Kernel functions, Optimal Hyperplane for linearly classifiable patterns, Optimal Hyperplane for non-separable patterns, SVMs for classification, K-means clustering.

Module-5: [4 Hours]
Introduction to Deep Learning: Deep neural networks, Convolutional Neural Networks (CNN), Applications of deep networks.

Module-6: [2 Hours]
Evaluation Measures: Confusion Matrix, Accuracy, Precision, Recall, Specificity, ROC.

Course Objective

1 .

To understand the different machine intelligence algorithms.

2 .

To design and development of the machine learning algorithms for solution of different problems.

Course Outcome

1 .

1. To know key concepts and principles of machine intelligence, including supervised, unsupervised, and reinforcement learning.
2. To study and apply Bayesian classifier and parameter estimation techniques.
3. To understand and apply different machine learning models e.g. EM algorithm, Neural networks like Support Vector Machine to solve different problems.
4. To study and apply different techniques for dimensionality reduction of features
5. To understand and analyze the performance of machine intelligence models using different evaluation measures.

Essential Reading

1 .

Kelvin P. Murphy, Machine Learning-A probabilistic Perspective, MIT Press , 2012

2 .

C. M. Bishop, Pattern Recognition and Machine Learning, Springer , 2013

Supplementary Reading

1 .

Tom M. Mitchell, Machine Learning, McGraw Hill Education (India) , 2013

2 .

Ethem Alpaydin, Introduction to Machine Learning, MIT Press , 2nd edition, 2010.