Coffee Talk: Homelessness and Hunger Panel Discussion

EE Graduate Seminar

Stochastic Graph Grammars

Prof. Tim Oates
Associate Professor of Computer Science
Computer Science and Electrical Engineering, UMBC

11:30am Friday November 11, ITE 231, UMBC

Many important domains are naturally described relationally, often using graphs in which nodes correspond to entities and edges to relations. Stochastic graph grammars compactly represent probability distributions over graphs and can be learned from data, such as a set of graphs corresponding to proteins that have the same function.

In this talk we consider the problem of learning the parameters (i.e., the production probabilities) of stochastic graph grammars and the structure of the grammar (i.e., the productions) given a representative sample of graphs taken from the underlying distribution. We also present efficient algorithms for computing properties of the distribution over graphs defined by a graph grammar such as expectations of graph size, node degree, and number of edges.

Dr. Tim Oates is an Associate Professor in the CSEE Department at UMBC. He received B.S. degrees in Computer Science and Electrical Engineering from North Carolina State University in 1989, and M.S. and PhD degrees from the Univ of Massachusetts Amherst in 1997 and 2000, respectively. Prior to coming to UMBC in Fall 2001, Prof. Oates spent a year as a postdoc in the Artificial Intelligence Lab at MIT.

Host: Prof. Joel M. Morris

EE Graduate Seminar

Stochastic Graph Grammars

Prof. Tim Oates
Associate Professor of Computer Science
Computer Science and Electrical Engineering, UMBC

11:30am Friday November 11, ITE 231, UMBC

Many important domains are naturally described relationally, often using graphs in which nodes correspond to entities and edges to relations. Stochastic graph grammars compactly represent probability distributions over graphs and can be learned from data, such as a set of graphs corresponding to proteins that have the same function.

In this talk we consider the problem of learning the parameters (i.e., the production probabilities) of stochastic graph grammars and the structure of the grammar (i.e., the productions) given a representative sample of graphs taken from the underlying distribution. We also present efficient algorithms for computing properties of the distribution over graphs defined by a graph grammar such as expectations of graph size, node degree, and number of edges.

Dr. Tim Oates is an Associate Professor in the CSEE Department at UMBC. He received B.S. degrees in Computer Science and Electrical Engineering from North Carolina State University in 1989, and M.S. and PhD degrees from the Univ of Massachusetts Amherst in 1997 and 2000, respectively. Prior to coming to UMBC in Fall 2001, Prof. Oates spent a year as a postdoc in the Artificial Intelligence Lab at MIT.

Host: Prof. Joel M. Morris

The Team for Research in Ubiquitous Secure Technology (TRUST) will sponsor 20 undergraduate students from diverse backgrounds and cultures, to participate in the Summer Undergraduate Research Experience located at TRUST partner campuses: UC Berkeley, Cornell University, Stanford University, Vanderbilt University. These students will work with graduate student and faculty mentors throughout the summer performing research and supporting activities in the area of information technology and TRUST related topics. The program will run from June 3 to July 27, 2012 and provide room and board, a travel allowance and a $4,000 stipend. Apply by February 17. See the flyer for more information and the Trust REU site for details and to apply.

The Team for Research in Ubiquitous Secure Technology (TRUST) will sponsor 20 undergraduate students from diverse backgrounds and cultures, to participate in the Summer Undergraduate Research Experience located at TRUST partner campuses: UC Berkeley, Cornell University, Stanford University, Vanderbilt University. These students will work with graduate student and faculty mentors throughout the summer performing research and supporting activities in the area of information technology and TRUST related topics. The program will run from June 3 to July 27, 2012 and provide room and board, a travel allowance and a $4,000 stipend. Apply by February 17. See the flyer for more information and the Trust REU site for details and to apply.

If you were among the millions who bought the new iPhone 4S, then you can thank Dr. Harry Chen, the UMBC alumnus who helped develop the phone’s most notable new feature: Siri.

For those not among the millions, here’s a bit of background:  Siri is a virtual assistant that responds to voice commands. “She” can do things like make phone calls, send text messages, set alarms, and find directions. But, the remarkable thing about Siri is that she understands intent. Tell Siri “I’m drunk,” and she’ll bring up a list of cab services in the area. Tell Siri “I want a burger” and she’ll direct you to burger joints nearby, according to ratings.   

Before Siri was bought by Apple, it was a small startup company operating out of Silicon Valley. Born out of a research project of SRI International, the company functioned under the moniker “stealth-company.com” until they were ready to disclose what they were working on, says Chen, who joined the team when he was offered a job by Adam Cheyer, one of the company’s initial founders.  

The offer came at an ideal moment, after Chen and his wife had decided to start fresh on the West Coast. “We just packed and started looking for jobs,” says Chen who knew that Silicon Valley was the sort of culture he wanted to be in. But, when they made the move in 2008, he had no idea that he would end up contributing to one of the world’s most revolutionary technologies. “It has been a rollercoaster ride for me the past three years,” he says.

It’s no surprise that at UMBC, Chen studied artificial intelligence. He was a founding member of the Ebiquity group, named for its focus on Ubiquitous Computing—the idea that computing devices will seamlessly blend into our environment and enhance our everyday activity. While pursuing a Ph.D. in Computer Science at UMBC, Chen wrote his dissertation on intelligent rooms—rooms with the potential to collect information about their environment to share with different smart devices.

As a Graduate Student, Chen worked as a Research Assistant under Dr. Tim Finin. The position gave him the opportunity to meet other researchers in his field of study–like Cheyer, the man who would eventually offer him a place at Siri. Chen credits Dr. Tim Finin with pushing him forward: “Without him, I would probably not arrive where I am today.”

Today, Chen is a Siri Engineer at Apple and he loves it. “Apple is a very different company,” says Chen, who explains that the company runs more like a start-up than a big corporation. He couldn’t be happier with his decision to switch coasts. He sees Silicon Valley as the center of technological progress. “Reputable companies like Google, Facebook, Apple, Yahoo, Netflix, LinkedIn and Oracle are only a short drive from each other,” he says, “Cool new technologies tend to emerge within the Bay Area and then later spread throughout the world.”

Chen compares the evolution of Siri to a parent watching his child grow up. Though, it isn’t done growing–Chen predicts that the application will continue to improve. Siri is bound to become a model for the future of technology. Everyone—especially children and the elderly–will benefit by being able to interact with a computer just as they would a person: through speech. At least, so says Chen: “The natural evolution is natural language.”

Photo Courtesy Gizmodo.com