Building a car is hard. Building a propane/electric hybrid car from scratch using only volunteer labour in less than six months is, some would say, impossible.

Luckily, nobody mentioned that to Douglas Venn (MechE 6T9, MEng 7T1).

“We had no idea how impossible it was,” he says. “We just did it.”

Fifty years ago this summer, Venn led a team of students and professors in designing and building Miss Purity, a low-emission vehicle that competed in the Clean Air Car Race of 1970. The vehicle embodies the creativity, ingenuity, and determination that define the U of T Engineering spirit.

Venn grew up in Toronto and admits to being “car crazy,” as a youth. He built or rebuilt a number of hot rods, vintage and sports cars, entering them in local competitions and even on occasion taking the top prize.

But during his undergraduate engineering program, he started thinking more about alternative vehicles.

“I was following the work of William Lear, founder of Learjet,” he says. “He was experimenting with steam-powered cars, which I thought was just fantastic because a steam engine gives peak torque at stall, and you can use almost any fuel you want.”

Cars running on anything other than gasoline or diesel were a pretty far out idea at a time when public attitudes toward automobiles were very different than they are today.

“If you look at cars of that time, which are vintage cars now, they were really huge,” says Juri Otsason (MechE 7T0, MASc 7T2), another member of the team. “Fuel was cheap. All that mattered was performance.”

That was beginning to change in the late 1960s, as cities such as Los Angeles started to get serious about dealing with smog. Formed primarily from vehicle emissions — including carbon monoxide, nitrogen oxides and unburned hydrocarbons — smog has been linked to respiratory conditions and other health issues.

“In Los Angeles at that time, you often couldn’t see the tops of the buildings through the smog,” says Otsason.

It was in this atmosphere that Venn headed to Detroit for the January 1970 Congress of the Society of Automotive Engineers (SAE). There, he heard Professor Richard Thornton recount the story of the Great Electric Car Race of 1968, which pitted a team of his students at MIT against one from Caltech.

Then Thornton mentioned that he, along with staff and students from Caltech, was planning to organize another such race that summer, one that would be open to any university.

“My ears perked up,” says Venn. “I spoke to Thornton after the talk, and he was very keen to get a team from Canada, because it would open up their national event into an international one.”

Venn headed back to U of T with a mission: to convince his fellow students, along with faculty supervisors, to enter the competition by building a low-emission vehicle from scratch in less than six months.

“A lot of people thought we were crazy,” says Otsason, one of the first students Venn was able to bring on board. Another early convert and enthusiastic supporter was mechanical engineering professor Phil Hughes.

“He was one of the loveliest people I ever met, just like a kindly grandfather,” says Venn. “I remember him saying ‘By Jove, I think this is a smashing idea!’”

Rounding out the team were Steve Baker (MechE 7T2), Simon Ng (ElecE 7T1), and nearly a dozen other students. Faculty advisors included Hughes, as well as mechanical engineering professors I.W. Smith, and F. Hooper, and electrical engineering professor R.S. Segworth.

It quickly became clear that the steam power concept would be too complicated and expensive given the time constraints. Instead, the team opted for a hybrid design: a combustion engine running on propane — a cleaner-burning fuel than gasoline — coupled with an electric drive system that would be more efficient at lower speeds.

Another key decision was to bring on board Venn’s cousin Ken Bell, then a student at the Ontario College of Art and Design, to create the car’s exterior. The result was striking: Bell designed a sleek, futuristic-looking vehicle, complete with gullwing doors.

“They looked cool, but there was a practical consideration as well in that they left more room for the batteries,” says Otsason. The design eerily anticipated the DeLorean, the vehicle made famous in the Back to the Future films, which was then still years away from production.

Miss Purity began to attract attention almost immediately. Over the next six months, there were what Venn describes as “an increasing number of television appearances, as well as newspaper and magazine articles.”

Read more about Miss Purity and the Clean Air Car Race in archived articles from the New York Times, Popular Mechanics, Hemmings Motor News, and Automotive Fleet Magazine.

One of the highlights was a visit from officials from the National Air Pollution Control Administration (NAPCA), the forerunner of the Environmental Protection Agency (EPA).

“To say that they were excited by the U of T project would be an understatement,” says Venn. “They were thrilled, I think because not many of the teams were building cars from scratch the way we were.”

NAPCA even commissioned a short movie to document the Clean Air Race of 1970, narrated by Hollywood actor Orson Welles. Copies are hard to find these days, but Miss Purity features prominently in the film.

The press coverage increased further as the actual race started in August of 1970. Miss Purity turned heads everywhere she went.

“The race organizers had arranged events in every city,” says Otsason. “In Toronto, all the cars went down to city hall, and mayor Dennison came out to meet us. It was really something.”

This archival video from the Associated Press covers the Clean Air Car Race. The Toronto stop is featured from 2:40 to 4:00.

Venn remembers being asked by the race organizers to deliver banquet invitations using Miss Purity to then-governor of Massachusetts Francis Sargent and the mayor of Boston. The deliveries went well, but afterward, the car wouldn’t start.

“The front page of the Boston Globe was taken up by a photograph of Miss Purity being pushed by us,” he says. “The headline read ‘This car doesn’t pollute — not when muscle-powered!’”

The technical glitch wasn’t the only one. Early one morning, about halfway through the race, just outside of East St. Louis, a major breakdown nearly took Miss Purity out completely.

“The engine and most of the electric drive had to be completely torn out,” says Venn. “Luckily, we were close to a very supportive Chevrolet dealership that gave us a bay and provided the necessary parts.”

With their help, the car was repaired the same day. “We put the car back together and drove through the night to catch up with the race in Odessa, Texas,” says Venn. “Nobody could believe it!”

After more than 5,500 km of driving, the race came to an end in Pasadena, California. Miss Purity tied for first place among the hybrid cars, sharing the prize with a team from Worcester Polytechnical Institute, who were driving a modified AMC Gremlin.

Counting the return trip, which went through Vancouver and across Canada back to Toronto, Miss Purity was driven more than 16,000 km. She was sold for one dollar to the National Research Council in Ottawa for a further two years of research work, overseen by another U of T mechanical engineering graduate, Don Buchan.

In the years after the race, Venn partnered with some of the U of T Engineering professors involved to create a spinoff company, Vehicle Research, Ltd., that aimed to build electric vehicles for the consumer market.

“We had the very first three-phase induction, AC-driven electric car in the world, the same kind of drive now used by Tesla,” he says. “Unfortunately, the idea was way too far ahead of its time, and we didn’t have the deep pockets of Elon Musk.”

Venn eventually took a job designing household appliances, but he remained strongly involved in the automotive world through his continued membership in SAE.

In 2015, Venn was speaking to his friend Ron Passer about the project. After watching the movie of the race together, they decided to track down the car and see if it could be restored.

“The vehicle was found in Don Buchan’s front yard in Ottawa, where it had ‘lived’ for a number of years,” says Venn. Passer trailered the car back to his shop in Schomberg, Ont. and separated the body from the chassis.

Both are now being restored in partnership with Plastiglas Industries Ltd. in Ajax, Ont., which was founded by Miss Purity team member and driver, Steve Baker along with his brother Rick Baker just after the race.

For Venn, the legacy of Miss Purity has a lot to do with the community that it brought together.

“If we had thought too much about some of the challenges we would face, it’s possible some of us may have been overwhelmed, but that’s not the attitude we brought,” says Venn. “There’s a lot of capability within the human spirit. Impossible or not, there are times when you just have to do it.”

Fifty years after the Clean Air Car Race, practically all cars are now much ‘cleaner ’than in 1970, with the happy consequence that smog has been greatly reduced in many urban areas.

But pollution is still very much with us, and rising atmospheric concentrations of CO2 remain a challenge, one which Otsason believes still resonates with the story of Miss Purity.

“It drove home the point that there are ways of dealing with the problems we face in terms of pollution or emissions,” says Otsason. “I think she inspired people to look for alternatives, and we’re still doing that today.”

Video slideshow, part 1: Miss Purity 1970 — The Build

 

Video slideshow, part 2: Miss Purity 1970 – Clean Air Car Race Plus Pre and Post Activities

 

Video slideshow, part 3: Miss Purity 2020 – The Restoration

-This story was originally published on the University of Toronto’s Faculty of Applied Science and Engineering News Site on August 24, 2020 by Tyler Irving

U of T Engineering professor Steven Waslander (UTIAS) is developing the next generation of unmanned aerial vehicles (UAVs), better known as drones, that are capable of high-speed maneuvers, automated landing and stable flight near obstacles.

“This work could greatly expand the applications quadrotor drones are useful for,” explains Waslander. “The more advanced they become, the better they’ll be at inspecting infrastructure, search and rescue in remote environments, tracking moving objects for security, and delivering light-weight packages.”

But to succeed, his team needs the necessary state-of-the-art equipment to make it happen. Waslander is among five U of T Engineering researchers to receive funding through the Canada Foundation for Innovation’s (CFI) John R. Evans Leaders Fund (JELF), announced today.

The fund provides researchers with foundational tools and infrastructure, enabling research discovery and innovation. Funding was awarded to 33 projects across the University of Toronto, totalling more than $9.5 million.

For Waslander, the CFI JELF will go towards acquiring the latest in motion-capture cameras for real-time, high-accuracy motion tracking of drones, as well as a dedicated GPU server, for rapid graphics processing, to improve vehicle modelling through reinforcement learning.

The team is partnering with tech company NVIDIA, which will provide the GPU cluster, and Vicon Industries Inc for the cameras. This equipment will be deployed within an innovative indoor flight arena, located at the U of T Robotics Institute in the Myhal Centre for Engineering Innovation & Entrepreneurship

With the setup, Waslander and his team will test automated drones as they track a moving ground rover within the flight arena. “We want to execute repeated landings on the moving vehicle, maintaining the relative position accuracy to within 10 centimeters, even as the speed of the target vehicle increases,” says Waslander, who is working with Ford Motor Company and Drone Delivery Canada as a first application of this method.

“Foundational research infrastructure, coupled with world-class researchers, leads to groundbreaking discoveries,” says Ramin Farnood, U of T Engineering’s Vice-Dean of Research. “With the support of CFI, our U of T Engineering researchers can continue to be leaders in their field and make positive, vital contributions to our society and the economy.”

The U of T Engineering CFI JELF recipients in this round are:

• Leo Chou (BME) —DNA Nanotechnology for spatially programmed immune receptor activation
• Jane Howe (MSE, ChemE) — Advanced scanning electron microscope for in situ and liquid-phase electron microscopy study
• Goldie Nejat (MIE) — Robotics infrastructure for smart manufacturing (RISM)
• Nicolas Papernot (ECE) — Trustworthy machine learning
• Steven Waslander (UTIAS) — Autonomous docking and active perception for unmanned aerial vehicles

-This story was originally published on the University of Toronto’s Faculty of Applied Science and Engineering News Site on August 19, 2020 by Liz Do

 

Zero-emission sources of power harvested from solar and wind are less costly and more widely available than ever before. But what happens when the sun doesn’t shine or the wind doesn’t blow? Professor Aimy Bazylak (MIE) may have an answer.

Bazylak holds the Canada Research Chair in Thermofluidics for Clean Energy. Her research program focuses on two complementary technologies: electrolyzers and fuel cells.

Electrolyzers use electricity to drive a chemical reaction, such as splitting water into hydrogen and oxygen. Fuel cells reverse this process, turning stored chemical energy back into electricity.

“When fed hydrogen, fuel cells can produce zero-emission power on demand,” says Bazylak. “I’m excited and driven by the vital role that clean energy technology must play for a sustainable future.”

Another application of electrolyzers is the electro-reduction of carbon dioxide. This chemical reaction is the first step in a complex process that can upgrade waste carbon into valuable products, such as plastics or fuels. This process increases the economic incentives for carbon capture and storage.

Whether they are upgrading captured carbon or producing hydrogen to store renewable electricity, electrolyzers rely on the efficient transport of flows through porous materials. Bazylak and her team study ways to optimize these components.

Leveraging their expertise in microfluidics, they are designing better fuel cell and electrolyzer materials and architectures to increase overall efficiency or reduce undesirable side effects, such as water buildup that degrades performance.

For her contributions to fuel cell and electrolyzer technology, Bazylak was named this year’s winner of the McLean Award. The $125,000 award, jointly funded by the Connaught Fund and the McLean endowment, recognizes early career researchers and supports outstanding basic research in the fields of computer science, mathematics, physics, chemistry, engineering sciences and the theory and methods of statistics.

“I feel deep gratitude for receiving the McLean Award,” says Bazylak. “I’m tremendously excited about the privilege this provides to both advance clean energy with my team as well as support the growth and development of junior researchers.”

Bazylak says that the funding will also support efforts to further increase diversity in scholarship and research.

“The scientific community lacks diversity, and barriers and discrimination are systemic issues,” she says. “The McLean Award will help me and my team to grow allyship for equity, diversity, and inclusivity in clean energy, and thereby embrace a certainly tremendous untapped potential of up and coming leaders of tomorrow.”

“On behalf of the Faculty, my warmest congratulations to Professor Bazylak on this well-deserved award,” says Ramin Farnood, Vice-Dean, Research at U of T Engineering. “Her dynamic team is at the forefront of innovation in sustainable energy, and she has demonstrated a strong commitment to building a more inclusive community.”

-This story was originally published on the University of Toronto’s Faculty of Applied Science and Engineering News Site on August 21, 2020 by Tyler Irving

The MIE Department was deeply saddened to learn of the passing of Dr. Henry Moller in June 2020. Moller was a PhD candidate in the Department of Mechanical and Industrial Engineering working with the Interactive Media Lab to evaluate his innovative TEMM (technology-enhanced multimodal meditation) virtual reality system. In Dr. Moller’s memory, and to honour his contributions to his PhD research, the Faculty of Applied Science and Engineering along with family and friends have established the Henry Moller Graduate Scholarship.

Dr. Moller dedicated his professional life to holistic patient mental health and wellness. He obtained his Doctor of Medicine degree in 1996 from the University of Toronto and specialized in Psychiatry at McMaster University in 2001. In 2014, he opened his psychiatric practice with a focus on community-centred long-term patient wellness. The clinic provided a safe space for his diverse patient community and he was known for exploring the Danforth neighbourhood with interested patients in a weekly walking group during his lunch breaks. Dr. Moller worked hard to better understand his patients’ cultural contexts and issues to provide more effective long-term support. He remained a dedicated care provider throughout the COVID-19 pandemic, supporting patients through telephone and video consults.

In 2016 Dr. Moller began collaborating with the Department of Mechanical and Industrial Engineering to address how to best support the changing relationships and conditions of mental health, urbanization and aging. His project, titled Windows to the World, looked at how immersive mindfulness meditation assisted by virtual reality (VR) could improve mental health and wellbeing, particularly in patients experiencing anxiety or depression. Using VR headsets and a combination of high quality video footage and overlaid computer graphics that he created, Moller immersed patients into beautiful and calming natural scenes and experiences most people would not be able to see, like sunrise in the Swiss Alps. He studied how the brain reacted to these images and considered adjustments and enhancements that could be made for better results as part of an iterative design process; adding sounds, animals, or even a voice to guide the patient through the meditative experience.

“Henry’s approach to health and wellbeing was truly holistic,” Professor Mark Chignell, the director of the Interactive Media Lab noted. “His research will help maximize the benefits of a kind of mindfulness meditation gained from immersive interactions with natural scenes, and make leisure therapy more accessible and available to those who need it.”

Moller’s study into how VR tools can be used to help treat anxiety and depression will continue in the Interactive Media Lab. The team will continue on with the process of testing different combinations of sounds and images to see how the brain reacts and how the greatest benefits can be reached.

In his personal life, Dr. Moller was a lover of travel, art and music. He was a member of the Toronto Choral Society and was passionate about exploring different cultures and sharing them with his loved ones. His creativity, sensitivity and generosity of spirit both set him apart and helped him succeed in his career. He will be greatly missed by his family, friends and colleagues.

In memory of Dr. Henry Moller the Faculty of Applied Science and Engineering along with family and friends have established the Henry Moller Graduate Scholarship. The scholarship will be awarded to future graduate students in the Interactive Media Lab, who demonstrate academic excellence and who are undertaking advanced research relating to mental wellness and multimedia.

-Published August 13, 2020 by Lynsey Mellon, lynsey@mie.utoronto.ca

Congratulations to Birsen Donmez, Roy Kwon and Lidan You on their recent promotion to Professor. The Department is also celebrating Amy Bilton and Eric Diller for receiving tenure and being promoted to Associate Professor.

		Professor Birsen Donmez joined the Department of Mechanical & Industrial Engineering in January 2010. Her research interests are centered on understanding and improving human behavior and performance in multi-task and complex situations, using a wide range of analytical techniques. In particular, her research focuses on operator attention in multitask activities, decision support under uncertainty, and human automation interaction, with applications in various domains including surface transportation, healthcare, mining, and unmanned vehicle operations. She has served on multiple committees of the Transportation Research Board of the National Academies, as an associate editor for IEEE Transactions on Human-Machine Systems, and as the General Chair for AutomotiveUI’18.
		Roy H. Kwon is a professor in the Department of Mechanical & Industrial Engineering and is also a member of the faculty in the Masters of Mathematical Finance (MMF) Program at U of T. His research focuses on financial engineering (portfolio optimization, asset allocation, risk management, and option pricing) and supply chain management (logistics and production control). Dr. Kwon has published articles in such journals as Management Science, Naval Research Logistics, the European Journal of Operational Research, and Operations Research Letters, among others. In addition, he has worked and consulted in the use of operations research (optimization) for the military, financial, and service sectors.
		Dr. Lidan You holds cross-appointments in the Department of Mechanical & Industrial Engineering (MIE) and the Institute of Biomaterials and Biomedical Engineering (IBBME). She is the director of Cellular Biomechanics Laboratory at U of T. Her research is focused on solving biomechanical questions in muscular skeletal system at the cellular level.In specific, her team is working on the anti-resorptive effect of mechanical loading on bone tissue; pressure effect on bone cell mechanotransduction; osteogenic potential of high frequency low magnitude vibration on bone adaptation; angiogenesis involvement in initiation of bone resorption under disuse condition; the advanced microfluidic system for bone cell mechanotransduction study; the role of focal adhesion assembly in cell mechanosensitivity using micropatterned surface; and the development of advanced artificial bone matrix by employing novel microfabrication technologies.
		Amy Bilton joined the Department of Mechanical & Industrial Engineering as an Assistant Professor in January 2014. Dr. Bilton’s research lies at the intersection of developing theoretical design and control techniques and developing new physical electromechanical systems. Applications of her research include water purification systems, desalination systems, and renewable energy. Her current work is focused on deployment of a newly developed solar-powered water purification system in the developing world.
		Dr. Eric Diller joined the Department of Mechanical & Industrial Engineering in January 2014 as an Assistant Professor. His work is enabling a new approach to non-invasive medical procedures, micro-factories and scientific tools. He does this by shrinking the mechanical and electrical components of robots to centimeter, millimeter or even micrometer size. He uses magnetic fields and other smart-material actuation methods to make mobile functional devices. Dr. Diller envisions a future where drug delivery and surgery can be done in a fast, painless and focused way, and where new materials and devices can be manufactured using swarms of tiny gripping, cutting, and sensing wireless robots.

-Published August 7, 2020 by Lynsey Mellon, lynsey@mie.utoronto.ca

Elias Khalil obtained his PhD in Computational Science and Engineering from Georgia Tech (2019), a MS in Computer Science from Georgia Tech (2014), and a BS in Computer Science from the American University of Beirut (2012). His research interests are in Artificial Intelligence with a focus on machine learning and discrete optimization. Professor Khalil is joining the Department of Mechanical and Industrial Engineering as an Assistant Professor.

What drew you to MIE at U of T and made you eager to accept a position here?

I chose MIE at U of T for a number of compelling reasons: strong research programs, excellent graduate students, a friendly community of faculty and staff, many potential faculty collaborators both in MIE and at the university-level, ambitious plans to grow Artificial Intelligence within Engineering, and a great, welcoming, diverse city.

What is the most memorable experience in your career so far?

Halfway through my master’s studies in the US, I started working on my thesis. The result I was seeking seemed out of reach at first; I was only starting out with research and the theory I was looking to derive was complicated. One of the most memorable experiences I’ve had so far in my career was proving that theorem. It took many iterations and really pushed my limits at the time, and I remain proud of that result. The thrill of making a dent on a research problem, which I first experienced then, remains the main driver for me.

Can you share a little about your research and what you like about it?

Much of my research centers around the following question: how do we design optimization algorithms that improve with experience? Much of our modern world’s operations boil down to solving optimization problems: assigning delivery trucks to routes such that transportation cost is minimized; managing inventory to minimize storage and service costs subject to varying customer demand; choosing which land parcels to conserve to maximize the probability of species conservation; allocating physicians to patients based on expertise and availability to maximize health outcomes.

Designing algorithms that work very well for a particular optimization problem can be a tedious task for us humans, both for theoretical and practical reasons: how should a truck routing algorithm behave differently when used to optimize daily delivery routes in Toronto vs Montreal? The post office might need a PhD-level computer scientist or operations research specialist to analyze the data and modify existing algorithms to achieve improved performance in both cases. It is often easier to design algorithms that work OK on a class of optimization problems, but then that might not be enough for the end-user: we want really good algorithms so we can make better decisions, save on time and computing resources and solve more challenging problems.

This is where my research comes in: I design machine learning methods that leverage historical data to redesign or re-purpose optimization algorithms such that they perform better on a problem we care about. My research draws on a mix of techniques from computer science, machine learning/artificial intelligence and operations research, and I am interested in applications in supply chain management, urban planning and healthcare.

What do you hope to accomplish, as an educator and as a researcher, over the next few years?

In research, I am excited to work with students and collaborators to push the frontier in this new area of “data-driven algorithm design”, both on the theoretical and applied fronts. In education, I hope to show students the connections between data, algorithms, and applications and help them develop into multi-faceted engineers that can bring these technical skills into applications.

Do you have any advice for incoming students?

For undergraduates: concepts that may seem far removed from the real world can turn out to be really useful down the line if you put in the effort to understand them. For graduate students: read a lot of research papers and textbooks so you can quickly become an expert at a few select topics, and be nice to other researchers (let them know if you like their work!).

Do you have a favourite spot on campus or in Toronto?

I’ve only been in Toronto for a few weeks, but I already like the Back Campus Fields which often have a bunch of pick-up soccer games going every day during the summer.

-Published August 6, 2020 by Lynsey Mellon, lynsey@mie.utoronto.ca

Professor Aimy Bazylak is one of five outstanding researchers to be recognized with the Helmholtz International Fellow Award. This award, established by the Helmholtz Association of German Research Centres, recognizes researchers who have excelled in their work in Helmholtz-relevant areas and already have an ongoing cooperation with at least one of the Helmholtz Centers. The aim of the award is to continue to strengthen collaborations between the world’s best researchers.

Prof. Bazylak was nominated by the Karlsruhe Institute of Technology (KIT) to receive this prestigious award for her work in sustainable energy. Bazylak’s research is focused on fuel cells, hydrogen generation, carbon dioxide reduction, and batteries through the design of microscale and nanoscale porous materials for custom heat and mass transfer, high surface areas, thermal storage, and multiphase transport. She examines the interplay between solids, liquids, and gases within porous materials to advance the state-of-the-art in electrochemical energy conversion.

“I’ve developed strong collaborations with the researchers at the Helmholtz Association across Germany,” said Bazylak, “and in particular with Dr. Roswitha Zeis at the Helmholtz Institute of Ulm (HIU) and the Karlsruhe Institute of Technology (KIT), who specializes in high temperature fuel cells and redox flow batteries.”

As a Helmholtz International Fellow, Prof. Bazylak will receive €20,000 of research funding and have the opportunity to pursue her research at one or more of the Helmholtz Centres. The award will be used to further more research with her German collaborators in the area of clean energy.

-Published August 5, 2020 by Lynsey Mellon, lynsey@mie.utoronto.ca

Sinisa Colic completed his PhD at the University of Toronto in the area of personalized treatment options for epilepsy using advanced signal processing techniques and machine learning. He was then a postdoctoral fellow at McMaster University where he worked with medical imaging data for the diagnosis and treatment of mood disorders. Professor Colic has taught several courses at University of Toronto covering a broad range of topics in mechatronics and machine learning and is now joining us an Assistant Professor, Teaching Stream.

What drew you to MIE at U of T and made you eager to accept a position here?

I came to U of T because of its world-renowned research and quality of education. I stayed because of the many remarkable people that I’ve met, the beautifully diverse Toronto community, and the many possibilities in AI research and technology. MIE is leading the way in applied AI research and offers some of the most cutting edge courses at University of Toronto, which I am very excited to be a part of.

What is the most memorable experience in your career so far?

That would probably be the yearly MIE444 design competition which I have been fortunate to coordinate for the past 4 years. The competition involves students designing and prototyping an autonomous rover to find, pick-up, and drop off a wooden block. Year after year, I am impressed with our students’ tremendous skill, creativity and determination.

Can you share a little about your research and what you like about it?

Most recently I have been working on applying machine learning techniques to characterize the electrical activities in the brain for the diagnosis and treatment of mood disorders such as depression, schizophrenia, and suicidal ideation. I’m excited about this work because it could allow people to better manage their mental health and achieve their full potential.

What do you hope to accomplish, as an educator and as a researcher, over the next few years?

As a researcher, I hope to develop a mental health management tool that will allow for fast and reliable identification of mental instabilities to help improve people’s quality of life. As an educator, I would like to provide a good balance between theory and application, to best prepare students for real world challenges.

Do you have any advice for incoming students?

Take every opportunity you can to share your experiences, help others learn what you know, and apply what you have learned to projects you are passionate about.

Do you have a favourite place on campus or in the city?

This is a very difficult question. Toronto has so many interesting neighbourhoods with their own unique feel. If I have to pick, I would say Christie Pits Park is my favourite spot in the city.

-Published August 4, 2020 by Lynsey Mellon, lynsey@mie.utoronto.ca

Zheda Mai (MASc Student), Jihwan Jeong (PhD Candidate), Prof. Scott Sanner and team member Hyunwoo Kim (LG Sciencepark) won first prize in all categories in the CLVision Challenge held at the 2020 virtual Computer Vision and Pattern Recognition (CVPR) conference. Their entry beat out 79 other teams including some top Continual Learning/Computer Vision teams in the world from both industry and academia.

Continual learning is the ability of a system to continuously learn and adapt from the data it collects over time This requires the system to be able to learn the current task without forgetting the ability to perform well in all previously seen tasks. It poses a huge challenge due to device storage limits that don’t allow for the option to repeatedly review all previously seen data. Continual learning is often applied in low power and memory devices such as cell phones and will play an increasingly integral role in Artificial Intelligence systems that continually learn and adapt to the data they take in.

The CLVision Challenge asked competitors to submit continual learning solutions for three different challenge tracks: New Instances (NI), Multi-Task New Classes (Multi-Task-NC) and New Instances and Classes (NIC). Teams had the option to submit to one or all three of these tracks and the competition was held in two separate phases, pre-selection and final evaluation. The LG & University of Toronto team easily made it into the final evaluation phase and ranked number one in all three categories to win first prize overall.

“I was very excited to take part in this competition as it allowed us to apply novel continual learning solutions and provided a comprehensive evaluation on a shared hardware platform for a fair comparison,” Zheda said, “Each solution was evaluated across a number of metrics, including accuracy, ram usage, running time, etc. This made the competition more challenging since we need to strike a balance between all the metrics.”

Zheda and his team presented a continual learning method called batch-level experience replay with review in their entry. In this method a memory buffer stores samples of each task that is completed. When the system is asked to preform a new task, it reviews and learns from the samples stored in the memory buffer. They used this method and its variants on all three tracks set forth in the CLVision Challenge and achieved impressive results.

To learn more about the CLVision Challenge and the University of Toronto & LG Science Park submission you can review their paper online.

-Published July 8, 2020 by Lynsey Mellon, lynsey@mie.utoronto.ca