X

Optimisation for Machine Learning: Theory and Implementation (Hindi)

By Prof. Pravesh Biyani   |   IIIT Delhi
Learners enrolled: 4553
ABOUT THE COURSE:
Optimisation is the workhorse of machine learning. Knowing optimisation is a key prerequisite in understanding theory and practise of machine learning. In this course, we will discuss the foundations required for solving optimization problems in the context of machine learning through various case-studies/running-examples. We will start with covering the basics of linear algebra and calculus required for learning optimization theory. We will learn both the theory and implement optimization algorithms like stochastic gradient descent and its various variants to solve machine learning problems of classification, clustering etc using standard problem formulations which are convex (SVM etc) and non-convex (Neural Networks and Deep Neural Networks) etc.

INTENDED AUDIENCE: UG/PG

PREREQUISITES: Linear Algebra, Calculus, Basic Programming

INDUSTRY SUPPORT: Google, Microsoft, Facebook, Amazon, Flipkart and all companies connected to Data Science, Signal Processing and AI/ML
Summary
Course Status : Completed
Course Type : Elective
Duration : 8 weeks
Category :
  • Computer Science and Engineering
Credit Points : 2
Level : Undergraduate/Postgraduate
Start Date : 20 Feb 2023
End Date : 14 Apr 2023
Enrollment Ends : 20 Feb 2023
Exam Registration Ends : 17 Mar 2023
Exam Date : 29 Apr 2023 IST

Note: This exam date is subjected to change based on seat availability. You can check final exam date on your hall ticket.


Page Visits



Course layout

Week 1 : Basics of Linear Algebra and Calculus: Subspaces, EigenValue Decomposition, Singular Value Decomposition - Algorithms and Methods, PSD Matrices and Kernel Functions, Vector Calculus
Week 2 : Basics of Linear Algebra and Calculus: Subspaces, EigenValue Decomposition, Singular Value Decomposition - Algorithms and Methods, PSD Matrices and Kernel Functions, Vector Calculus(Continue...)
Week 3 : Convex Functions, First and Second Order Conditions for Optimisations, Convex and Non Convex Optimisation problems in Machine Learning
Week 4 : Gradient Descent: math, programming basic optimisation problems and their solutions
Week 5 : Variants of Gradient Descent: Projected, Stochastic, Proximal, Accelerated, Coordinate Descent, Training a Neural Network: Theory
Week 6 : Variants of Gradient Descent: Projected, Stochastic, Proximal, Accelerated, Coordinate Descent, Training a Neural Network: Theory(Continue...)
Week 7 : Newton’s Method, Optimization for ML in practice: Pytorch/Tensor Flow. Training a Neural Network, Implementation
Week 8 : Newton’s Method, Optimization for ML in practice: Pytorch/Tensor Flow. Training a Neural Network, Implementation(Continue...)

Books and references

1. Foundations of Data Science, Avrim Blum and Ravi Kannan, Hindustan Book Agency/Cambridge University Press
2. Linear Algebra and Learning from Data, Gilbert Strang
3. Convex Optimisation by Stephen Boyd
4. Optimisation for Machine Learning by Suvrit Sra, MIT Press.

Instructor bio

Prof. Pravesh Biyani

IIIT Delhi
Prof. Pravesh Biyani was born in Raigarh, India and received his BTech from IIT Bombay in 2002 and MS from McMaster University in the year 2004. He have also worked at the Ikanos Communications while pursuing his PhD at the IIT Delhi till early 2012. In the later 2012, he was a post- doctoral researcher at the University of Minnesota, Minneapolis with Prof. Tom Luo. He have won the INSPIRE Faculty award by the Govt. of India in 2012 and am currently an INSPIRE faculty at the IIIT Delhi. His research interests are physical layer wireless and wireline communications, optimization for signal processing and machine learning. Recently he have developed interest in applying ideas from Convex Optimization in solving problems in urban transportation, specially the bus route network design problem.

Course certificate

The course is free to enroll and learn from. But if you want a certificate, you have to register and write the proctored exam conducted by us in person at any of the designated exam centres.
The exam is optional for a fee of Rs 1000/- (Rupees one thousand only).
Date and Time of Exams: 29 April 2023 Morning session 9am to 12 noon; Afternoon Session 2pm to 5pm.
Registration url: Announcements will be made when the registration form is open for registrations.
The online registration form has to be filled and the certification exam fee needs to be paid. More details will be made available when the exam registration form is published. If there are any changes, it will be mentioned then.
Please check the form for more details on the cities where the exams will be held, the conditions you agree to when you fill the form etc.

CRITERIA TO GET A CERTIFICATE

Average assignment score = 25% of average of best 6 assignments out of the total 8 assignments given in the course.
Exam score = 75% of the proctored certification exam score out of 100

Final score = Average assignment score + Exam score

YOU WILL BE ELIGIBLE FOR A CERTIFICATE ONLY IF AVERAGE ASSIGNMENT SCORE >=10/25 AND EXAM SCORE >= 30/75. If one of the 2 criteria is not met, you will not get the certificate even if the Final score >= 40/100.

Certificate will have your name, photograph and the score in the final exam with the breakup.It will have the logos of NPTEL and IIT Madras .It will be e-verifiable at nptel.ac.in/noc.

Only the e-certificate will be made available. Hard copies will not be dispatched.

Once again, thanks for your interest in our online courses and certification. Happy learning.

- NPTEL team


MHRD logo Swayam logo

DOWNLOAD APP

Goto google play store

FOLLOW US