Scribd
Upload
157 views

ML Syll

This document outlines the course objectives, units, instructional hours, outcomes and references for a Machine Learning course. The course aims to provide students with the mathematical background and concepts of machine learning, expose them to supervised, unsupervised and semi-supervised learning algorithms, and applications in wireless communication, biomedical and security domains. It is a 3 credit hour course divided into 5 units covering topics such as linear algebra, probability, neural networks, machine learning in wireless/security, and biomedical applications. The expected outcomes are for students to demonstrate understanding of ML principles and techniques and be able to formulate ML problems for different applications.

Uploaded by

murlak37
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
157 views

ML Syll

This document outlines the course objectives, units, instructional hours, outcomes and references for a Machine Learning course. The course aims to provide students with the mathematical background and concepts of machine learning, expose them to supervised, unsupervised and semi-supervised learning algorithms, and applications in wireless communication, biomedical and security domains. It is a 3 credit hour course divided into 5 units covering topics such as linear algebra, probability, neural networks, machine learning in wireless/security, and biomedical applications. The expected outcomes are for students to demonstrate understanding of ML principles and techniques and be able to formulate ML problems for different applications.

Uploaded by

murlak37
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 2

Programme Course Code Name of the Course LTPC

ME 20CMX312 Machine Learning 3 0 0 3

Course Objective
1. To study the Mathematical background of machine learning.
2. To enable the student to understand the concept of machine learning.
3. To learn the fundamentals of different Neural network architectures.
4. To know the machine learning application in wireless communication and bio-medical.
5. To expose the student to be familiar with a set of well-known supervised, semi-supervised and unsupervised learning
algorithms

Unit Description Instructional Hours


I MATHEMATICAL BACKGROUND 9
Linear Algebra – Arithmetic of matrices, Norms, Eigen decomposition, Singular value decomposition, Pseudo inverse,
Component analysis. Probability theory – probability distribution, conditional probability, Chain rule, Bayes rule,
Information theory, Structured Probabilistic models.

II MACHINE LEARNING BASICS 9


Supervised and Unsupervised learning, Capacity, Over fitting and Under fitting, Cross Validation, Linear regression,
Logistic Regression, Regularization, Naive Bayes, Support Vector Machines (SVM), Decision tree, Random forest, K-
Means Clustering, k nearest neighbor.

III NEURAL NETWORKS 9


Feed forward Networks , Back propagation, Convolutional Neural Networks-Le-Net, Alex-Net, ZF-Net, VGG-Net,
Google-Net, Res-Net, Visualizing Convolutional Neural Networks, Guided Back propagation, Deep Dream, Deep Art,
Fooling Convolutional Neural Networks. Recurrent Neural Network (RNN) – Back propagation through time (BPTT),
Vanishing and Exploding Gradients.

IV ML IN WIRELESS AND SECURITY 9


Water-filling power allocation, Optimization for MIMO Systems, OFDM Systems and MIMO-OFDM systems.
Optimization in beamformer design – Robust receive beamforming, Transmit downlink beamforming. Application: Radar
for target detection, Array Processing, MUSIC, ML in Side channel analysis.

V ML IN BIO-MEDICAL 9
Machine Learning in Medical Imaging. Deep Learning for Health Informatics. Deep Learning Automated ECG Noise
Detection and Classification System for Unsupervised Healthcare Monitoring. Techniques for Electronic Health Record
(EHR) Analysis.
Total Instructional Hours 45
Course Outcome
After completion of the course the learner will be able to
CO1: Demonstrate understanding of the mathematical principles underlying machine learning.
CO2: Familiar with the different machine learning techniques and their use cases.
CO3: In a position to formulate machine learning problems corresponding to different applications.
CO4: Able to recognize the characteristics of machine learning techniques that are useful to solve real-world problems.
CO5: In a position to read current research papers, understand the issues and the machine learning based solution
approaches.
REFERENCE BOOKS:
R1-Ian Goodfellow, Yoshua Bengio, and Aaron Courville, “Deep learning”, Cambridge, MA, MIT Press, 2017.
R2-Tom M. Mitchell, “Machine Learning”, McGraw Hill, 1997.
R3-Ethem Alpaydın, “Introduction to machine learning”, MIT Press, 3rd Edition, 2014.
R4-M. N. Wernick, Y. Yang, J. G. Brankov, G. Yourganov and S. C. Strother, “Machine Learning in Medical Imaging”,
IEEE Signal Processing Magazine, vol. 27, no. 4, pp. 25-38, July 2010.
R5-Ravì et al., “Deep Learning for Health Informatics,” IEEE Journal of Biomedical and Health Informatics, vol. 21, no.
1, pp. 4-21, Jan. 2017.
R6-U. Satija, B. Ramkumar and M. S. Manikandan, “Automated ECG Noise Detection and Classification”, IEEE Journal
of Biomedical and Health Informatics PP(99), March 2017.
R7-“System for Unsupervised Healthcare Monitoring,” IEEE Journal of Biomedical and Health Informatics, vol. 22, no.
3, pp. 722-732, May 2018.
R8-B. Shickel, P. J. Tighe, A. Bihorac and P. Rashidi, “Deep EHR: A Survey of Recent Advances in Deep Learning
Techniques for Electronic Health Record (EHR) Analysis,” IEEE Journal of Biomedical and Health Informatics, vol. 22,
no. 5, pp. 1589-1604, Sept. 2018.
R9-A. Heuser, S. Picek, S. Guilley and N. Mentens, “Lightweight Ciphers and their Side-channel Resilience,” IEEE
Transactions on Computers.

You might also like