Computer Science

Localizing epilepsy ‘hotspots’

Student interns worked this summer with the Davis Lab in the Penn Epilepsy Center to research improvements to epilepsy diagnosis using the tools of machine learning and network analysis.

Brandon Baker

Working to keep Penn ‘cyber safe’

Media hacks and data breaches are everywhere. Nick Falcone of Penn’s Office of Information Security works to keep the University’s information assets safe, from employing phishing-simulation tools to monitoring attack trends across all schools and centers.

Phyllis Holtzman

Three Penn faculty named 2019 AAAS Fellows

Three from Penn have been named to the American Association for the Advancement of Science’s newest class of Fellows: Carolyn Gibson of the School of Dental Medicine, Sampath Kannan of the School of Engineering and Applied Science, and Ellen Puré of the School of Veterinary Medicine.

Katherine Unger Baillie

Media Contact

In the News

U.S. News & World Report

The AI revolution: For patients, promise and challenges ahead

Ravi Parikh of the Perelman School of Medicine said the use of machine learning in health care can be a double-edged sword. "Even though you might have an AI that's accurate on the whole, if it's mischaracterizing an outcome for a specific group of patients you really have to question whether it's worth it," he said.



These iPhone apps know how you’ll spend and save money—even before you do

Mauro Guillén of the Wharton School weighed in on personal finance apps for smartphones. “With digital technology, the possibilities expand,” he said. “I think we’re just seeing the beginning.”


The New York Times

An algorithm that grants freedom, or takes it away

An algorithm created for the Philadelphia Adult Probation and Parole Department by Richard Berk of the School of Arts and Sciences tries to improve on human judgement by excluding data that could be a proxy for race. “All machine-learning algorithms are black boxes, but the human brain is also a black box,” he said.


Experts warn smartphone voting is ‘extremely risky,’ yet here it comes

Matt Blaze of the School of Engineering and Applied Science weighed in on a Washington state district’s plans to implement smartphone voting. “This extremely risky decision runs counter to the findings of the authoritative National Academies ‘Securing the Vote’ study, which represents the consensus of experts,” he said.


PBS NewsHour

Ransomware and data breaches linked to uptick in fatal heart attacks

Ross Koppel of the School of Arts and Sciences spoke about the need for data standards in managing electronic medical records. “The classic line is that these data standards are like toothbrushes,” he said. “Everybody wants one, but they don’t want to share.”



A.I. is just as good as medical professionals at spotting disease, study says

Tessa Cook of the Perelman School of Medicine commented on the results of a study exploring the use of artificial intelligence in detecting disease. “Perhaps the better conclusion is that in the narrow public body of work comparing A.I. to human physicians, AI is no worse than humans, but the data are sparse and it may be too soon to tell,” she said.