Teaching and learning
Teaching
Graduate TA- Purdue ECE
Prepare and grade assignments, conduct office hours, and invigilate exams. I engage with students, coordinate the piazza sessions answering questions, and help the instructor manage the class.
- ECE301 Signals and Systems, Fall 2024
Visiting Instructor- ENTC, University of Moratuwa
I assist the lecturers in assignment preparation, evaluations, laboratory work, and invigilation of examinations. Additionally I conduct reviews on problem sets, and conduct extra sessions when students request additional help or tutoring.
- EN4553 Machine Vision, Fall 2023
- EN3551 Digital Signal Processing, Fall 2023
- EN3160 Fundamentals of Image Processing and Machine Vision, Fall 2023
- EN2412 Electronic Control Systems, Fall 2022
- EN2091 Laboratory practise and projects, Fall 2022
Tutor- Skill Surf
- STAT/CSE4340 Statistical Methods for Engineers, Fall 2022
- MATH3304 Introduction to Linear Algebra, Spring 2023
Learning
Graduate studies
Courses taken at Purdue Unviersity offered by the College of Engineering, and College of Sciences.
Core courses
- ECE6000 Random Variables and Signals with prof. Mary Comer.
- ECE6410 Model-Based Image and signal processing with prof. Charles Bowman.
- ECE5240 Machine learning with prof. Stanley Chan.
- ECE5130 Diffraction, Fourier Optics, and Imaging with prof. Stanley Chan.
- ECE6370 Digital Image ProcessingI with prof. Charles Bowman.
- ECE6450 Estimation Theory with prof. David J. Love.
” Math be mathin’ “
- MA 5110 Linear Algebra with applications with prof. M. Sunkula
- ECE6020 Lumped System Theory with prof. Stanislaw Zak.
A selection from undergraduate days
While following these modules and gaining theoretical knowledge, I have experience projects and publications in related research. Gradually I discovered my passion for underlying stochastic processes and in the theory of machine learning.
Advanced Courses
- EN4573 Pattern Recognition and Machine Intelligence:
- Covered Random Matrices, Multivariate Gaussian Density, Concentration of Measure in high dimensions, Goals of Learning, Randomness of the Generalization error, Inductive bias, Density estimation, Concentration inequalities, Introduction to PAC inequalities. Mostly from Statistical Learning Theory by Bruce Hajek and Justin Raginsky.
- EN4583 Advances in Machine Vision
Mathematical fundamentals
- MA4033 Time Series and Stochastic Processes
- MA4013 Linear Models and Multivariate Statistics
- MA3023 Numerical Methods
- MA3013 Applied Statistics
- MA2053 Graph Theory
- MA2033 Linear Algebra
- MA2023 Calculus
- MA2013 Differential Equations
Signal/Image Processing and Telecommunications
- EN4553 Machine Vision
- EN4053 Digital Communications II
- EN3053 Digital Communications I
- EN2570 Digital Signal Processing
- EN2550 Fundamentals of Image Processing and Machine Vision
- EN2083 Electromagnetics
- EN2040 Random Signals and Processes
- EN1060 Signals and Systems
Computer Engineering
- EN3240 Embedded Systems Engineering
- EN3143 Electronic Control Systems
- EN3030 Circuits and System Design
- EN2030 Fundamentals of Computer Organization and Design
MOOCs
- Mathematics for Machine Learning- Imperial College London- (Coursera) August 2020
- Neural Networks and Deep Learning- Deeplearning.AI (Coursera) July 2020
- Computational Thinking and Datascience- MIT 6.00.2 (EdX) June 2020
- Machine Learning- Stanford University (Coursera) May 2020