Mathematical Optimization with Applications in Machine Learning

START:
June 24, 2019
DURATION:
5 Days
ID:
1028
CREDITS:
2
FEE:
PES Participants:
Rs. 5,000
Non-PES Participants:
Rs. 10,000

INSTRUCTORS:

Nagegowda K S
Associate Professor

Address

Crucible of Continuing Education (CCE)
PES University Campus
100 Feet Ring Road, BSK III Stage
Bengaluru – 560 085   View map

About the Course


Machine learning is an interdisciplinary field in the intersection of mathematical statistics and computer sciences. Machine learning studies statistical models and algorithms for deriving predictors or meaningful patterns from empirical data. Machine learning techniques are applied in search engine, speech recognition and natural language processing, image detection, robotics etc.. In our course we address the following questions: What is the mathematical model of learning? How to quantify the difficulty/hardness/complexity of a learning problem? How to choose a learning algorithm? How to measure success of machine learning?

Course Objectives

Most Machine Learning, AI, Communication and Power Systems problems are in fact optimization problems.  The objective of this short course is to familiarize participants with the basic concepts of mathematical optimization and how they are used to solve problems that arise in above mentioned areas.

Who should attend
Undergraduate Students, Beginning Graduate Students and Research Scholars

Out station students / candidates have to make their arrangements for accommodation and boarding

Course Outline and schedule


Day-01


Introduction to mathematical optimization, Classification of optimization problems, Taylor’s Series.
Programming Hands on: Contours for different values of the objective function, Newton-Raphson Method.

Day-02


Least Square Problems
Programming Hands on: Linear and Polynomial models fitting

Day-03


Brief Introduction Neural Networks, Application to Neural Networks and Algorithms for mathematical optimization.
Programming Hands on: Solving non-linear least square problems using Gauss-Newton Method

Day-04


Convex Optimization – Application to Support Vector Machines
Programming Hands on: Applying Convex optimization to Linear Programming and SVM

Day-05


Non-Convex Optimization – Expectation Maximization, Bayesian inference, Convergence and correctness of ML algorithms.
Programming Hands on: Likelihood estimation.

Evaluation and Assessment: Instructor will provide Project statement which includes list of algorithms. The student has to choose an algorithm and apply techniques taught in the course to optimize the chosen algorithm.


Share this page


TOP