Machine learning: Data, data everywhere, but not enough to think


December 6, 2019

Imagine a smartphone app that can identify whether your pet is a cat or dog based off a photo. How does it know? Enter machine learning and an unimaginable amount of data.

But teaching a machine is more complicated than just feeding it data, says Pavan Turaga, an associate professor in Arizona State University's School of Electrical, Computer and Energy Engineering and interim director of the School of Arts, Media and Engineering, who is trying to find ways to revolutionize the way machines learn about the world. Three men posing in front of monitor Pavan Turaga (left) and his research team are applying geometry and topology to machine learning models to make them more efficient and less reliant on large quantities of data. Photo courtesy of Pavan Turaga Download Full Image

“The work that I’m doing is leaning toward the theoretical aspects of machine learning,” Turaga said. “In current machine learning, the basic assumption is that you have these algorithms that can try to solve problems if you feed them lots and lots of data.”

Turaga’s research, which has numerous applications in the defense industry, is supported by the Army Research Office, an organization within the U.S. Army Combat Capabilities Development Command’s Army Research Laboratory.

But at the base of many of machine learning’s applications, no one knows how much data is actually needed to obtain accurate results. So, when the model doesn’t work, it’s difficult to understand why.

For simple apps like pet identification, it is relatively inconsequential if the program is wrong. However, more critical applications of machine learning, such as those found in self-driving cars, can have more detrimental impacts if they operate incorrectly.

“Many times, you do not actually have the ability to create such large datasets, and that’s why many of these autonomous systems are being held back from mission-critical deployment,” Turaga said. “If something is mission critical, on which people’s lives depend and on which other large investments depend, there is skepticism on how these things will pan out when we don’t really know the breakdown.”

Relying solely on data, a self-driving car might incorrectly identify a person on a street corner as stationary when the person is actually planning on crossing the street, or a home security sensor could completely miss detecting an intruder or incorrectly identify certain events.

Improving machine learning by studying geometry and topology

In the real world, there are countless variables that can produce endless outcomes, and it would take an ever-increasing amount of data to account for every circumstance that could potentially occur. Even for identifying objects, machines would need an innumerable amount of data to be able to recognize any given object in any orientation, and in any lighting condition.

But why reinvent the wheel when we can supplement machine learning with basic principles that have already proven?

Much like students in the Ira A. Fulton Schools of Engineering at ASU, machines have to learn the proven laws of the physical world.

“It seems like machine learning is creating its own separate representations of the world, which may or may not be rooted in basic things, like Newton’s laws of motion, for instance,” said Turaga, who leads the Geometric Media Lab at ASU. “So, there is a big disparity between what is known and what machine learning is attempting to do. We are at an intersection of trying to fuse these two to create more robust models, which can work even if we don’t have access to extremely large datasets.”

Turaga’s research involves applying two principles, Riemannian geometry and topology, to provide constraints to machine learning and reduce the size of the dataset needed to “teach” machines.

Riemannian geometry essentially is the study of smoothly curved shapes. It can be used to help mathematically describe ordinary objects using physics-based constraints.

Topology is the study of an object’s geometric properties that remain unchanged through the object’s deformation. For example, if you open and then close a pair of scissors, the shape of the scissors looks extremely different, but the object itself and most of its properties do not change.

In his research, Turaga has looked at multiple objects and modeled them using equations. In doing so, he has found that concepts from Riemannian geometry and topology appear to keep repeating themselves again and again.

“It turns out that if you know a little bit more about the kind of object you’re looking at, such as whether it’s convex-shaped, that provides a nice mathematical constraint,” Turaga said.

Getting back to object basics can improve three areas of machine learning

Not every physical principle can be efficiently accounted for, but by applying these new methods, Turaga hopes to see three main improvements to machine learning accomplished by his research: better interpretability, more versatility and higher generalizability.

“If we succeed in this research endeavor, one thing we’ll see is machine learning models becoming a little more interpretable — meaning when they work, or even when they fail, we will be able to explain the phenomenon in a way that relates to known knowledge about the world, which at this point does not exist,” Turaga said.

With better interpretability, machine learning errors can be better understood, corrected and improved, speeding up the overall rate at which autonomous systems can be developed and implemented.

Furthermore, Turaga’s research is expected to make machine models more adaptable.

For example, if a machine is first tested in a lab and then deployed on a ship, it will be subject to extremely different conditions than it was in the laboratory setting. Instead of trying to retrain the machine from scratch, Turaga hopes to be able to provide the machine with information based on known principles of the new environment and fine-tune its performance using small datasets during deployment.

Finally, Turaga expects machine learning to become faster and more efficient. He says training machine learning models is currently a huge energy sink, consuming electricity at a rate comparable to what is needed to supply power to a small country.

Increasing the efficiency of machine learning will also have environmental benefits.

On its current track, machine learning could “undo all the good things we are doing to make our world more energy efficient,” Turaga said. “But I believe if we are successful in training machine models faster by using knowledge from physics and mathematics, then the whole field can reduce its carbon footprint.”

Karishma Albal

Student Science/Technology Writer, Ira A. Fulton Schools of Engineering

480-283-5304

Outstanding grad overcame personal, academic challenges to complete online program


December 6, 2019

Editor’s note: This is part of a series of profiles for fall 2019 commencement.

For Wendi Malmgren, it took a community of friends, fellow students, teachers, tech support staff and field instructors to facilitate her success as a graduate in the Master of Social Work online program at Arizona State University Wendi Malmgren, Watts College School of Social Work outstanding graduate fall 2019. Wendi Malmgren, fall 2019 outstanding graduate, School of Social Work, Watts College of Public Service and Community Solutions Download Full Image

Several difficulties presented themselves to the School of Social Work’s fall 2019 Outstanding Graduate. The biggest: During her course of study, Malmgren had to deal with the deaths of two immediate family members.

As a returning student, she found the online program technology to be daunting, and considered transferring to the traditional classroom model. But through it all, Malmgren said she found ways to succeed. Her first ASU experience two decades ago, after all, was a rewarding one.

“My history with the university goes back 20 years, not as a student, but working with faculty in the theater department to develop and sustain an arts-against-violence program and provide an alternative field education experience for theater majors,” she said.

Malmgren had been in the social work field for those two decades before realizing she was ready for a new challenge.

“I wanted to add depth and breadth to my academic experiences, and ultimately want to obtain a clinical license in social work,” she said.

“As a single mother who raised two daughters, I understand many of the challenges facing women in today’s world,” she said. “I believe that women’s rights are human rights, which must be honored and protected."
— Wendi Malmgren

Malmgren, from Phoenix, is a member of the second cohort of the online MSW program. She said that changing from the classroom to online was frustrating at first. But within the first few weeks she was able to reach out to other students, instructors and tech staff, and with their support, began to embrace the new learning opportunity.

That support enabled her to reach her goal and pursue her dream of practicing in the rural community where she has lived, completed an internship and plans to return: Coeur d’Alene, Idaho.

“Without that support and encouragement, I was ready to terminate my program and revert to the classroom model,” she said. “Ultimately the online program provided the flexibility to participate in my first internship in Coeur d’Alene and a second in Phoenix with ASU.” 

She said she is grateful for School of Social Work faculty members Associate Professor Joanne Cacciatore and Lecturer Jamie Valderrama for support and compassion while dealing with the deaths of her father and daughter during her program.

Both faculty members provided sensitivity and understanding at a time when Malmgren was seriously deciding whether to postpone her program or even go into another professional direction.

Once she returns to Idaho after graduation, Malmgren plans to take the Licensed MSW exam in January, then ultimately obtain a clinical license, which requires 3,000 hours of supervised practice.

If she were to be granted $40 million to solve one of the world’s problems, Malmgren said she’d use the money to advance women’s rights.

“As a single mother who raised two daughters, I understand many of the challenges facing women in today’s world,” she said. “I believe that women’s rights are human rights, which must be honored and protected."

Mark J. Scarp

Media Relations Officer, Watts College of Public Service and Community Solutions

602-496-0001