Technology Commercialization

By Professor Andrew Maxwell at York University in Winter 2017
Market adoption of new technologies is of concern to researchers, interested in creating economic value from their research, and attracting research. However, technology utility, by itself, is not sufficient to achieve commercial success. This course helps technologists understand the complex issues around enhancing the value proposition of novel technologies, and overcoming barriers to adoption through strategic partnerships or venture creation.

click here for more information about the course

Robot Mapping

By Professor Cyrill Stachniss from YouTube lectures in Summer 2016 (Online Lectures)

I viewed youtube lectures for this course.
The lecture covered different topics and techniques in the context of environment modeling with mobile robots. Course covered techniques such as SLAM with the family of Kalman filters, information filters, particle filters. Furthermore graph-based approaches, least-squares error minimization, techniques for place recognition and appearance-based mapping, and data association were investigated. The exercises and homework assignments also covered practical hands-on experience with mapping techniques, as basic implementations were a part of the homework assignments.

course web-page click here

Advanced Topics in Computer Vision: Convolutional Neural Networks

By Professor Richard Wildes at York University in Winter 2016
This course was a reading course which involved reading the existing literature on Convolutional Neural Networks being used by the Computer Vision Research community in most of the areas of vision. Most of the papers pertaining to the field of CNNs were read and discussed biweekly (twice a week) 4 papers per week and an extensive literature survey of CNNs being used for a specific topic was done towards the end of the course.

click here to download a literature review on Using CNNs for Low Level Vision

Principles of Distributed Computing

By Professor Eric Rupert at York University in Winter 2016

This course covers the fundamental principles of Distributed Systems. Topics covered in the course include:
  • shared-memory and message-passing models of distributed systems,
  • mutual exclusion,
  • agreement problems (consensus, leader-election, Byzantine agreement, approximate agreement),
  • broadcast and multicast algorithms,
  • impossibility results and lower bounds,
  • the consensus hierarchy,
  • implementing shared data structures,
  • randomization in distributed computing,
  • self-stabilization, and
  • a theoretical model for mobile computing

Topics in Machine Learning: Visual Perception for Autonomous Driving

By Professor Raquel Urtasun at University of Toronto in Winter 2016
This is a graduate course in visual perception for autonomous driving. The class covers topics in localization, ego-motion estimation, free-space estimation, visual recognition (classification, detection, segmentation), etc
course link

Download slides for Ethics for Autonomous Driving, click here.
click here to download course project report

Computer Vision

By Professor Minas Spetsakis  at York University in Fall 2015

This course covers the fundamental topics in Computer Vision. Topics covered in the course include:
  • Introduction.
  • Camera Geometry, Lighting, Image Formation.
  • Color
  • Linear filters
  • Image Features and Edge Detection
  • Stereo
  • Structure from Motion
  • Segmentation, Grouping and Model Fitting.
  • Visual Motion and Optical Flow.
  • Matching.

Data Mining

By Professor Aijun An at York University in Fall 2015

Data mining or knowledge discovery from databases (KDD) is one of the most active areas of research in databases. It is at the intersection of database systems, statistics, AI/machine learning, and data visualization. In this course, we will introduce the concepts of data mining and present data mining algorithms and applications. Topics include association rule mining, sequential pattern mining, classification models, and clustering.

click here to download course project report

Embodied Intelligence

By Professor John K. Tsotsos at York University in Winter 2015
Audited the course

This course is intended as a follow-on from a first course on Artificial Intelligence. Whereas such first courses focus on the important foundations of AI, such a Knowledge Representation or Reasoning, this course will examine how these separate foundational elements can be integrated into real systems. This will be accomplished by detailing some general overall concepts that form the basis of intelligent systems in the real world, and then presenting a number of in-depth cases studies of a variety of systems from several applications domains. The embodiment of intelligence may be in a physical system (such as a robot) or a software system (such as in game-playing) but in both cases, the goal is to interact with, and solve a problem in, the real world.