- unknown (b.)
Professor of Computer Science, she is fascinated by the concept of Artificial Intelligence. She explains what she does as "trying to get computers to do things that you would think were smart if people did them." She runs the Multi-Agent, Planning and Learning Lab (MAPLE) at UMBC, which focuses on developing A.I. solutions to real world problems. Within the realm of artificial intelligence, she has divided her research interests into the three areas within in her lab: Multiagent Systems, Planning, and Machine Learning. Multiagent Systems deals with the task of getting multiple intelligence systems, like humans or A.I.s, to solve problems together. Currently, she is interested in the problem of trust. She is working to understand how to know which agents—for example, restaurant or movie reviews, or travel services– in an online community are trustworthy and which are not. At the moment, she is working with a referring agent that she knows will overestimate an individual's ability and provide her with biased positive referrals. A biased agent, she explains, leads to the phenomenon of optimistic and pessimistic referrals. She is quoted as saying, "Planning focuses on the problem of trying to pre-plan in complex domains where planning is hard." She compares her work to the job of a logistics planner for a FedEx fleet who is bombarded with last minutes pick-ups and deliveries that dynamically change his anticipated plan. In both cases, the task is the same: "What can you do in advance to anticipate what the likely kinds of requests are and be prepared to change things quickly?" Machine Learning deals with building models to classify data or to make predictions. She explains the concept with an example, no doubt, close to home: predicting whether or not students will pass a class. "What are the attributes that actually lead to success or failure in that context," she says, "That's the model building question. But, in some cases, there is not enough data to build a model. If, for example, the model-builder does not know information such as the amount of hours each student spends doing homework, it becomes difficult to predict their success in class. That's where cost sensitive feature acquisition comes into play. This means that certain information can be collected, but if the model relies on that acquired information, then the model becomes severely limited by its necessity to have that information for all future predictions." She is especially interested in collaborating with students and helping them develop their own research interests. She says that nearly ninety-five percent of her research is with students. "I like the students to learn about a problem and find something that they think is interesting," she says. "The methodologies we use to identify and try to solve problems are things I'm starting to think about more explicitly," she said, mentioning that in the future she is interested in writing about how to do research effectively. Her ultimate vision; though she says it is probably too ambitious to realize, is an all-purpose A.I. that helps with computer maintenance and other tasks. "What I would love to exist by the time that I retire is a true intelligent agent that would live on your laptop and monitor your life," she says.
Noted For:Currently doing research to understand how to know which agentsâ€”for example, restaurant or movie reviews, or travel servicesâ€“ in an online community are trustworthy and which are not
Category of Achievement: