Aaron Roth, PhD, UPenn Professor and Author of The Ethical Algorithm, Joins Spectrum Labs as Advisor

Share Article

Roth Adds Expertise to Spectrum’s Mission of Safety by Design and Flagging Toxic Behavior Online — Across Industries, Countries, and Languages.

Spectrum Labs, Inc, which uses Contextual AI to accurately recognize toxic behaviors online, today announced that Aaron Roth, PhD, will join its Board of Advisors to advance Spectrum’s twin missions of safety by design and training machines to flag toxic behaviors across industries, countries and languages. Dr. Roth will guide Spectrum as the company continues innovating in contextual AI with its next generation private machine learning platform. Included in these efforts are minimizing the need for direct access to sensitive data, minimizing the ability to reverse training, and reducing identity leakage.

Roth is the Bicentennial Term Associate Professor of Computer and Information Science at the University of Pennsylvania computer science department, associated with the theory group, PRiML (Penn Research in Machine Learning) the Warren Center for Network and Data Sciences, and co-director of UPenn’s program in Networked and Social Systems Engineering. He focuses on algorithms and machine learning — specifically on private data analysis, fairness in machine learning, game theory and mechanism design, and learning theory. He is also the recipient of a Presidential Early Career Award for Scientists and Engineers (PECASE), an Alfred P. Sloan Research Fellowship, an NSF CAREER award, a Google Faculty Research Award, an Amazon Research Award, and a Yahoo Academic Career Enhancement award.

Roth is also the co-author of a new book, “The Ethical Algorithm,” written for a general audience. Publisher Oxford University Press writes, “Understanding and improving the science behind the algorithms that run our lives is rapidly becoming one of the most pressing issues of this century. Traditional fixes, such as laws, regulations and watchdog groups, have proven woefully inadequate. Reporting from the cutting edge of scientific research, The Ethical Algorithm offers a new approach: a set of principled solutions based on the emerging and exciting science of socially aware algorithm design. Michael Kearns and Aaron Roth explain how we can better embed human principles into machine code - without halting the advance of data-driven scientific exploration. Weaving together innovative research with stories of citizens, scientists, and activists on the front lines, The Ethical Algorithm offers a compelling vision for a future, one in which we can better protect humans from the unintended impacts of algorithms while continuing to inspire wondrous advances in technology.”

“For us, adding Aaron Roth as an advisor seemed like a perfect fit: Just as Spectrum’s platform is constantly learning to recognize and flag the kinds of toxic behaviors that pollute users’ online experience, Spectrum as a company is constantly learning, as well. We are humbled and excited to learn from Aaron’s expertise and experience in designing machine learning with an eye to both innovation and ethics,” said Josh Newman, Spectrum Labs CTO. “We’re already working on some great projects together, so stay tuned,” Newman added.

About Spectrum Labs

Founded in 2016, Spectrum Labs’ Contextual AI platform helps online communities recognize and respond to toxic behaviors — like radicalization, sexual grooming, harassment and cyberbullying — in real time, across languages and content types. Our Data Vault, which contains an ever growing mix of data gathered from customers, researchers and third-party partners, powers community-specific signals we build for our customers so they can confidently take action against disruptive behaviors. Spectrum is based in San Francisco, California. For more information, visit getspectrum.io.

Share article on social media or email:

View article via:

Pdf Print

Contact Author

Lee Davis
Spectrum Labs
+1 (339) 236-0070
Email >

Lee Davis
@SpectrumLabsAI
since: 03/2017
Follow >
Visit website