top of page

Computer Vision

​The course covers the following topics

  1. Sensor Selection

  2. Image Processing and Analysis

  3. Motion Analyses

  4. 3D Reconstruction

  5. Pointcloud Processing

  6. Feature Tracking

  7. Object Detection.

3D reconstruction from stereo camera

Machine Learning and AI 

​​The course covers the following topics​

  1. Regression

  2. Parametric/Non-Parametric Learning

  3. Discriminative and Generative Algorithms

  4. Naive Bayes, Non‐linear Classifiers

  5. Feature Engineering/Representation

  6. Ensemble Methods

  7. Support Vector Machine (SVM)

  8. Unsupervised Learning and Clustering Algorithms

  9. Principal Component Analysis

  10. Neural Networks

  11. Training, Testing, and Evaluation

  12. Reinforcement Learning

image.png

Deep Learning

​​The course covers the following topics

  • Introduction to Deep Learning and its application

  • Neural Networks & Backpropagation

  • Convolutional Neural Networks (CNN)

  • Interpretability of Deep Learning

  • Graph Neural Networks (GNN)

  • Recurrent Neural Networks (RNN)

  • Variational Autoencoders (VAE) & Generative Adversarial Networks (GAN)

  • Deep Reinforcement Learning (DRL)

  • Solving Engineering problems using Deep Learning

Balancing of pendulum using policy gradient method shown on the right

dle.gif

Visual Learning and Recognition

​The course covers the following topics

  1. Visual Recognition

  2. Deep Learning

  3. Image Classification

  4. Object Detection

  5. Video Understanding

  6. 3D Scene Understanding

Screenshot 2024-09-01 060437_edited.jpg

Geometry Based Methods in Vision

​The course covers the following topics

1. Fundamentals of projective, affine, and Euclidean geometries

2. Projective Transforms in 2D and 3D

3. Single view geometry: The pinhole model

4. 2-view geometry: The Fundamental matrix

5. 2-view reconstruction

6. N-view reconstruction

7. Self-calibration

8. Learning-based SfM and SLAM

Assignment list and links can be accessed by clicking the "View More" button.

geomvis.gif

Advanced Engineering Computation

​​This course covers the following concepts, with assignments in C++

  1. Efficient data structures and algorithms for modeling and processing real-world data sets such as trees, hash tables, searching, priority queues, etc.

  2. Techniques for simulation and visualization such as numerically solving ODEs and PDEs, viewing control, programmable shader, etc.

  3. Tools for version controlling, scripting, and code building including sub-version, git, and cmake.

As part of the course project, I have successfully ported the classic Pac-Man game to C++. You can view a demo on the right, and access the complete code by clicking the "View More" button.

adec.gif

Engineering Optimization

​​This course covers the following concepts

  1. ​Model construction

  2. Sensitivity analysis

  3. Metamodeling 

  4. Constraint activity

  5. Nonlinear programming: necessary and sufficient conditions for optimality

  6. Numerical methods.

  7. Mixed-integer programming

  8. Convexification

  9. Global optimization

  10. Decomposition,

  11. Stochastic methods 

image.png

Trustworthy AI Autonomy

​​The course covers the following topic

  • Latent space visualization

  • Adversarial machine learning

  • Generative models

  • Rare-event learning

  • Sequential decisions making - model-free methods

  • Sequential decisions making - model-based methods

  • Stochastic functional approximation

  • ​Adversarial AI

  • Safe AI 

  • AI Evaluation

  • Hierarchical AI

    • Applied AI to real-world autonomy

image.png
bottom of page