Teaching and Invited Talks

Teaching

Advanced Topics in Deep Learning, CSC8852 (Graduate)

Fall 2022
This class on advanced topics includes:
(i) Unsupervised Learning Generative models - Autoregressive models, VAEs, GANs, (ii) Semi-supervised learning, (iii) Self-supervised learning, (iv) Active learning, (v) Attention models, (vi) Transferlearning/Domain adaptation, (vii) Diffusion models.
The average class strength is 13 students.

@ASU - Fundamentals of Statistical Learning, CSE 569 (Graduate)

Fall 2019, Fall 2018
This class on statistical learning includes:
(i) Bayesian parametric models, (ii) Parameter estimation like Maximum Likelihood, Expectation Maximization and Hidden Markov Models, (iii) Non-parametric models like clustering, Gaussian Processes and Gaussian Mixtures and (iv) Neural Network models.
The average class strength was 130 students.

@ASU - Introduction to Deep Learning for Visual Computing CSE 598 (Graduate)

Spring 2021, Fall 2019
The introduction to deep learning systems for computer vision includes:
(i) Linear models like Linear regression and Logistic regression, (ii) Multilayer neural networks, (iii) Optimization techniques for training deep neural networks, (iv) Convolutional neural networks, (v) Generative models like Variational Autoencoders, Generative Adversarial Networks and (vi) Transfer Learning.
The average class strength was 200 students.
This is an online course hosted on coursera.org as part of ASU's Online MCS Program.

@ASU - The ASU Experience ASU 101 (Undergrad)

Fall 2020, Fall 2019
This is an introductory course for ASU Freshman. The course includes topics on:
(i) Problem solving, (ii) Entrepreneurial vision, (iii) Social embeddedness, (iv) Sustainability challenges, (v) Academic integrity and (vi) Life-long learning.
The course had 3 sections with an average section strength of 20 students.

@ASU - Computer Science Capstone II CSE 486 (Undergrad)

Spring 2016
This is a senior undergrad course where students are trained to work in groups on industry projects in computer science. This is a culminating program designed to train students in software development, teamwork and communication.
The average class strength was 60 students.

@ASU - Principles of Programming Java CSE 110 (Undergrad)

Fall 2013
This is an introductory course in programming with Java. The course includes topics on:
(i) problem solving and algorithms, (ii) data types, (iii) control structures (if-else, for, while, switch), (iv) basic object oriented concepts (classes, objects, methods, parameters, overriding, overloading), (iv) arrays, searching and sorting.
The average class strength was 130 students.

@ASU - Teaching Associate

• CSE 100 - Principles of Programming C, 2011 - 2012

• CSE 110 - Principles of Programming Java, 2010 - 2014

• CSE 230 - Computer Organization/Assembly Language Programming, 2011

Invited Talks/Presentations

• Guest Lecture: Machine Learning Under Low Supervision, CSC8900 Seminar, Georgia State University, 2022.

• Invited Talk: Domain Adaptation in Vision with Deep Learning, Indian Institute of Technology, Ropar, India, 2021.

• Guest Lecture: Generative Adversarial Networks, CSE 494 Introduction to Machine Learning, Arizona State University, 2020.

• Invited Talk: /Citizen-centered Smart Cities and Smart Living, Vietnam Education Foundation Delegation, Arizona State University, 2019.

• Guest Lecture: Unsupervised Learning: Clustering and Dimensionality Reduction, Indian School of Business, Hyderabad, India, 2019.

• Guest Lecture: Hidden Markov Models and Expectation Maximization, CSE 569, Arizona State University, Summer 2019.

• Guest Lecture: Unsupervised Learning: Non-parametric Density Estimation, Hidden Markov Models and Gaussian Mixture Models, Indian School of Business, Hyderabad, India, 2019.

• Tutorial: Domain Adaptation in Computer Vision, International Conference on Smart Multimedia, Toulon, Cote D'Azur, France, 2018.

• Invited Talk: Deep Learning in Vision and Transfer Learning, Artificial Intelligence Club, Arizona State University, 2018.

• Guest Lecture: Introduction to Deep Learning, Domain Adaptation and Reinforcement Learning, CSE 572 Data Mining, Arizona State University, 2017.