Skip to content. Skip to navigation
CIM Menus
You are here:  CIM CIM Seminars Upcoming Seminars

CIM Seminar Series

CIM invites speakers with diverse interests to present seminars to its community on a regular basis. The details of next seminar scheduled are shown below. If the next seminar hasn't yet been scheduled, please check back soon. In the meantime, an overview of all seminars (past & future) can be perused by following the "All Seminars" link below.

Informal Systems Seminar (ISS), Centre for Intelligent Machines (CIM) and Groupe d'Etudes et de Recherche en Analyse des Decisions (GERAD)

Distributed Coordination for Network Optimization


Jorge Cortes
Department of Mechanical and Aerospace Engineering University of California, San Diego

March 24, 2017 at  11:00 AM
Room 4488, Andre-Aisenstadt Building, Universite de Montreal Campus, 2920 chemin de la Tour, H3T 1J4

The need for network optimization is pervasive, from the coordination of distributed energy resources in power networks to multi-sensor fusion and motion coordination in robotic networks, passing through traffic coordination at intersections of networked vehicles. From a systems and control perspective, such optimization problems pose formidable research challenges in order to guarantee the reliable, efficient, and safe operation of networked systems in real-world applications. This talk describes our progress on engineering networks with predictable behavior through the design of distributed coordination strategies. We deal with network optimization problems defined by separable convex objective functions encoding goals and performance metrics, and constraints that couple the state of individual agents encoding physical, communication, or operational specifications. In our discussion, we pay particular attention to establishing guarantees on algorithm correctness, characterizing the algorithm robustness against disturbances and communication link failures, and synthesizing opportunistic state-triggered coordination strategies for the efficient use of the available resources.

Informal Systems Seminar (ISS), Centre for Intelligent Machines (CIM) and Groupe d'Etudes et de Recherche en Analyse des Decisions (GERAD)

Reinforcement Learning Applications in Power Systems


Mohammed Abouheaf
Department of Electrical Engineering Ecole Polytechnique de Montreal

March 24, 2017 at  3:00 PM
McConnell Engineering Room 437

Reinforcement Learning is an area of machine learning concerned with how an agent can pick its actions in a dynamic environment to transition to new states, in such a way that maximizes a cumulative reward. Reinforcement Learning methods allow the development of algorithms to learn online the solutions to optimal control problems for dynamic systems that are described by difference equations. These involve two-step techniques, known as policy iteration (PI) or value iteration (VI).

The recent decades showed accelerated evolution of Reinforcement Learning applications in power Systems. Reinforcement Learning and optimization techniques are utilized to assess the security of the electric power systems and to enhance Microgrid performance. Adaptive learning methods are employed to develop control and protection schemes. Transmission technologies with High-Voltage Direct Current (HVDC) and Flexible Alternating Current Transmission System devices (FACTS) based on adaptive learning techniques can effectively help to reduce transmission losses and CO2 emissions.

In this talk, applications of Reinforcement Learning are highlighted for three research problems in power systems. First, Reinforcement Learning is used to develop distributed control structure for a set of distributed generation sources. The exchange of information between these sources is governed by a communication graph topology.

Second, an online adaptive learning technique is used to control the voltage level of an autonomous Microgrid. The control strategy is robust against any disturbances in the states and load. Only partial knowledge about the Microgrid's dynamics is required. Finally, Q-Learning with eligibility traces technique is adopted to solve the power systems non-convex Economic Dispatch problem with valve point loading effects, multiple fuel options, and power transmission losses. The eligibility traces are used to speed up the Q-Learning process.

The Perceptual Advantage of Symmetry for Scene Perception


Sven Dickinson
Dept. of Computer Science University of Toronto

March 30, 2017 at  2:00 PM
McConnell Engineering Room 437

Human observers can classify photographs of real-world scenes after only a very brief exposure to the image (Potter & Levy, 1969; Thorpe, Fize, Marlot, et al., 1996; VanRullen & Thorpe, 2001). Line drawings of natural scenes have been shown to capture essential structural information required for successful scene categorization (Walther et al., 2011). Here, we investigate how the spatial relationships between lines and line segments in the line drawings affect scene classification. In one experiment, we tested the effect of removing either the junctions or the middle segments between junctions.

Surprisingly, participants performed better when shown the middle segments (47.5%) than when shown the junctions (42.2%). It appeared as if the images with middle segments tended to maintain the most parallel/locally symmetric portions of the contours. In order to test this hypothesis, in a second experiment, we either removed the most symmetric half of the contour pixels or the least symmetric half of the contour pixels using a novel method of measuring the local symmetry of each contour pixel in the image. Participants were much better at categorizing images containing the most symmetric contour pixels (49.7%) than the least symmetric (38.2%). Thus, results from both experiments demonstrate that local contour symmetry is a crucial organizing principle in complex real-world scenes.

Joint work with John Wilder (UofT CS, Psych), Morteza Rezanejad (McGill CS), Kaleem Siddiqi (McGill CS), Allan Jepson (UofT CS), and Dirk Bernhardt-Walther (UofT Psych), to be presented at VSS 2017.