Relevant Coursework

click on the course to view the table of content

Instructor:
Prof. Kee-Eung Kim,
Graduate School of AI

Course Structure:
- Student Paper Presentations
- Final Project

Lectures:
- Introduction to RL
- Markov Decision Processes
- Planning by Dynamic Programming
- Model-Free Prediction
- Model-Free Control
- Value Function Approximation
- Policy Gradient Methods
- Integrating Learning and Planning
- Exploration and Exploitation
- Case study - RL in games

Instructor:
Prof. Edward Choi,
Graduate School of AI, (ex. Google Health Research, ex. intern Google Research, ex. internt DeepMind, etc.)

Course Structure:
- Weekly coding practice session (implementing all the topics covered in the lectures)
- 2 Projects

Lectures:
- Intro + Numpy
- Basic Machine Learning + Scikit-learn
- PyTorch Intro + Logistic Regression + Multi-layer Perceptron
- Autoencoders (& Denoising Autoencoders)
- Variational Autoencoders
- Generative Adversarial Networks
- Convolutional Neural Networks
- Word2Vec + Subword Encoding
- Recurrent Neural Networks & Sequence-to-Sequence
- Transformers
- BERT (& GPT)
- Image-Text Multimodal Learning
- Deep Diffusion Probabilistic Model
- Graph Neural Networks

Instructor:
Prof. Seunghoon Hong,
School of Computing, (ex Google Brain)

Course Structure:
- Coding assignments
- Paper presentation
- 40 Quizzes, each quiz is for one paper related to CVML

Lectures:
- Filters and detectors
- Blob detection and SIFT
- Image representation using local feature
- Support Vector Machine for classification
- Neural Networks
- Backpropagation
- Convolutional Neural Networks (CNN)
- Pytorch tutorial
- Semantic segmentation using CNNs
- Object detection and deformable part model
- CNNs for object detection
- CNNs for pose estimation
- Motion and optical flow
- Visual object tracking
- CNNs for object tracking
- CNNs for action recognition
- Attention in Vision

Instructor:
Prof. Tae-Kyun Kim,
School of Computing, (PhD from Cambridge, he is also affiliated with Imperial College London besides KAIST)

Course Structure:
- 2 paper review presentation
- 5 paper reviews (critique, similar to OpenReview)
- Project (involves writing a paper)

Lectures:
- Deep Learning (CNNs, optimization, batch normalization, dropout, ...)
- DNN architectures (ResNet, MobileNets, Knowledge distillation, ...)
- Benchmarks
- Advanced topics in DL (Bayesian CNNs, epistemic vs aleatoric uncertainty, graph CNNs, ...)
- GANs
- Reinforcement Learning
- DL for computer vision

Instructor:
Prof. Jaegul Choo
Graduate School of AI, (ex Georgia Tech)

Course Structure:
- Term Project
- Weekly paper review with summary and critique
- In-class quizzes every lecture

Lectures:
- Introduction to computer vision
- Convolutional neural networks and image classification
- Image captioning (Show, attend, and tell) & Object Detection (Fast R-CNN, Faster R-CNN, YOLO, SSD, ...)
- Semantic segmentation and instance segmentation (DeepLab and its variant models)
- Image generation (Basics of GANs, DCGAN, PGGAN, StyleGAN, VAE, PixelRNN, PixelCNN, ...)
- Image-to-image translation (Pix2Pix, CycleGAN, StarGAN, MUNIT, DRIT, ...)
- Self-supervised representation learning (MoCo, SimCLR, ...)
- Domain adaptation, meta-learning, few-shot learning, zero-shot learning (DANN, MAML, ...)
- 3D vision (Point clouds, 3D reconstruction)
- Multi-modal learning (CLIP, Dall-E, ...)
- Model interpretability (CAM, GradCAM, LIME, ...)
- User-interactive generative models (Interactive colorization, Interactive instance segmentation, GANDissect, ...)
- Data augmentation techniques (MixUp, CutOut, CutMix, ...)

Instructor:
Prof. Jaesik Choi, (PhD from Illinois at Urbana-Champaign)
Graduate School of AI

Course Structure:
- 2 programming assignments
- 2 source code reviews
- 2 source code implementations from scratch
- 1 paper/source code presentation
- 6 one-page paper reviews
- 1 term project

Lectures:
- Regularization for Deep Learning
- Optimization for Training Deep Models
- Practical Methodology
- Autoencoders
- Representation Learning
- Deep Generative Models
- Convolutional Neural Networks
- Recurrent Neural Networks
- Recurrent Neural Networks
- Autoenccoders & Variational Autoencoders
- Generative Adversarial Networks
- Generative Adversarial Networks

Instructor:
Prof. Sung-Ho Kim, (PhD from Carnegie Mellon University)
Dept of Mathematical Sciences

Lectures:
- Probability Theory
- Random Variables
- Discrete Probability
- Continuous Probability
- The Normal Distribution
- Descriptive Statistics
- Statistical Estimation and Sampling Distributions
- Inference on a Population Mean
- Comparing Two Population Means
- Discrete Data Analysis
- The Analysis of Variance
- Simple Linear Regression and Correlation
- Simple Linear Regression and Correlation
- Simple Linear Regression and Correlation

Instructor:
Prof. Kuk-Jin Yoon,
Dept of Mechanical Engineering, (Postdoc INRIA)

Course Structure:
- Coding assignments
- Project

Lectures:
- Introduction to Visual Intelligence
- Geometric Vision: Image Formation Model
- Geometric Vision: Single-view, Geometry and Camera Calibration Geometry
- Geometric Vision: Multiple-view
- Geometric Vision: Image Matching and Stitching
- Machine Learning and Deep Learning, Basics for Computer Vision
- 3D: Stereo
- Motion: Optical Flow
- 3D + Motion: Visual Odometry and SLAM
- Recognition: Image Features
- Recognition: Object Detection
- Object + Motion: Object Tracking
- Photometric Vision: Light and Color

Instructor:
Prof. Adil Mehmood Khan
Faculty of Computer Science and Engineering (Head of Lab of Machine Learning and Knowledge Representation at Innopolis University)

Course Structure:
- Assignments
- Participation (in-class quizzes to chosen students)
- Deep learing competition

Lectures:
- Bais-Variance Tradeoff
- Linear Regression
- Gradient descent, classification, logistic regression and confusion matrix
- Bayes classifier, Naive bayes classifier, KNN classifier, regularization and cross validation
- Separating hyperplanes, maximal margin classifier and SVM
- PCA
- Artificial neural networks and backpropagation
- CNNs
- Dropout, batch normalization, early stopping, transfer learning, data augmentation, etc.
- Decision trees
- Tree pruning, ensemble learning (bagging and boosting)
- Unsupervised learning, clustering, k-means clustering, k-means++, DBSCAN and hierarchical clustering

Instructor:
Prof. Alexandr Klimchik
Professor in Robotics (University of Lincoln)

Course Structure:
- Coding practice sessions
- Coding Assignments
- Coding Exams

Lectures:
- Intro to robotics, drones and self-driving cars
- Tutorial on ROS
- Rigid body, homogeneous transformation and direct kinematics
- Inverse kinematics
- Differential kinematics
- Geometric calibration
- Trajectory planning
- Dynamics of rigid body and robotic manipulator
- Dynamics: Lagrange and Newton-Euler formulation

Instructor:
Prof. Igor Gaponov
University College London

Course Structure:
- Lectures
- Practice coding sessions
- Project
- Quizzes

Lectures:
- Linear control (PD, PID)
- Feedback linearization
- Inverse dynamics
- Robust control

Instructor:
Prof. Sergei Savin
Center for Technologies in Robotics and Mechatronics Components

Course Structure:
- Lectures
- Project
- Assignments
- Exam

Lectures:
- Null space, row space, projectors
- Column space, left null space, control applications
- Least squares and quadratic programming
- Domain, convex domains
- Linear inequality representation of convex domains
- Linear programming
- Quadratically constrained quadratic programming and second-order cone programming
- Semindefinite programming
- Mixed integer convex programming
- Barrier functions
- Minimax

Instructor:
Prof. Ilya Afanasyev
Kazan Federal University (Intelligent Robotics Dep.)

Course Structure:
- Lectures
- Coding Assignments
- Quizzes

Lectures:
- Intro to Sensors and Sensing
- Measurements & Error Analysis
- Filtering, Kalman Filter
- Image sensors
- Camera calibration
- Stereo vision
- Depth camera, MS Kinect
- Sensor fusion. Multisensory systems
- LIDAR & SONAR
- Inertial sensors
- GPS
- Internal sensors
- Actuators, MEMS and Smart Sensors

Instructor:
Prof. Muhammad Fahim
Queen's University Belfast

Course Structure:
- Practice sessions
- Coding Exam
- Assignments
- Project

Lectures:
- Image Filtering
- Binary Vision
- Object Detection
- Image Features
- YOLO Algorithm
- GAN
- Face Detection and Recognition (Viola Jones)
- Hough Transform
- Semantic Segmentation
- Video Tracking

Instructor:
Prof. Alexandr Klimchik
Professor in Robotics (University of Lincoln)

Course Structure:
- Assignments
- Coding quizzes
- Coding midterm
- Coding final exam

Lectures:
- Finite element analysis
- Elastostatic Calibration: MSA
- Elastostatic modelling: Virtual Joint Modelling
- Robot Calibration: Advanced robot Calibration, dynamic calibration
- Design of experiments
- Kinematically redundant manipulators
- Parallel robots
- Cable-driven Robots
- Screw Theory
- PoE