Pedro Szekely

Creates learning tools that understand data semantics, enabling users to easily transform, integrate and analyze data from heterogeneous sources and services.

ISI News

Yolanda Gil Named ACM Fellow

ISI researcher and CS professor recognized for leadership in advancing the use of artificial intelligence in support of science, and for service to the community

Read More

Space Tech Expo: AMP SoCal Event Features Top CubeSate and Small Satellite Pioneers

Professor David Barnhart speaks at the Advanced Manufacturing Partners for Southern California exhibit

Read More

Genuine Interest in Bogus Bots

Emilio Ferrara's work in possible 2016 election consequences of fake Twitter bots has generated more than 40 news stories in international media, including the cover of MIT Technology Review.

Read More
See More Stories »

Feature Story

What's Going On: Unsupervised Learning

October 25, 2016

Greg Ver Steeg thinks there's less difference between supervised and unsupervised machine learning than might appear to be the case. At his early November seminar on unsupervised learning, Ver Steeg made that point through a series of creative analogies - and described the concrete ways in which his work appears to have contributed to a California Institute of Technology researcher's cancer remission.

At the seminar, part of ISI's "What's Going On" research breakfast series, Ver Steeg walked an audience of about 30 ISI colleagues through the distinction between supervised and unsupervised learning, beginning with photos that could qualify for adorable-cat YouTube videos.

Supervised learning, said Ver Steeg, involves "cute" data that is recognizable and has training labels, meaning data is designated as either "cat" or "not cat." While such data can be trained to millions of parameters, it's difficult to learn anything new, since the data already is known to be or not be a cat.

Conversely, "Unsupervised learning is the dark matter of artificial intelligence," he said. As in the universe, which is known to be mostly dark matter about which little is understood, most learning by humans and animals actually is unsupervised. In other words, how we learn is rarely as simple as dividing the world into cats and not-cats. We instead work with a vast range of information from which we unconsciously manage to identify elements, predict outcomes and discern vital relationships.Read More

ISI Annual Report

View the 2016 ISI Annual Report.

Meet Our Researchers

Events

Unless otherwise noted, seminars are open to the public.

Dec 16Mason Porter, UCLAAI Seminar

Multilayer Networks

11:00am - 12:00pm PST
See More Events »

ISI Seminar Series

Keep up-to-date with the ISI seminars by subscribing below. You will have the option of subscribing to individual seminar topics.

Subscribe to seminar notifications

Feature Story

What's Going On: Unsupervised Learning

October 25, 2016

Greg Ver Steeg thinks there's less difference between supervised and unsupervised machine learning than might appear to be the case. At his early November seminar on unsupervised learning, Ver Steeg made that point through a series of creative analogies - and described the concrete ways in which his work appears to have contributed to a California Institute of Technology researcher's cancer remission.

At the seminar, part of ISI's "What's Going On" research breakfast series, Ver Steeg walked an audience of about 30 ISI colleagues through the distinction between supervised and unsupervised learning, beginning with photos that could qualify for adorable-cat YouTube videos.

Supervised learning, said Ver Steeg, involves "cute" data that is recognizable and has training labels, meaning data is designated as either "cat" or "not cat." While such data can be trained to millions of parameters, it's difficult to learn anything new, since the data already is known to be or not be a cat.

Conversely, "Unsupervised learning is the dark matter of artificial intelligence," he said. As in the universe, which is known to be mostly dark matter about which little is understood, most learning by humans and animals actually is unsupervised. In other words, how we learn is rarely as simple as dividing the world into cats and not-cats. We instead work with a vast range of information from which we unconsciously manage to identify elements, predict outcomes and discern vital relationships.Read More