New Chip Opens Door to AI Computing at Light Speed

by Ian Scheffler

Computing at the speed of light may reduce the energy cost of training AI. (Narongrit Doungmanee via Getty Images)

Penn Engineers have developed a new chip that uses light waves, rather than electricity, to perform the complex math essential to training AI. The chip has the potential to radically accelerate the processing speed of computers while also reducing their energy consumption.

The silicon-photonic (SiPh) chip’s design is the first to bring together Benjamin Franklin Medal Laureate and H. Nedwill Ramsey Professor Nader Engheta’s pioneering research in manipulating materials at the nanoscale to perform mathematical computations using light — the fastest possible means of communication — with the SiPh platform, which uses silicon, the cheap, abundant element used to mass-produce computer chips.

The interaction of light waves with matter represents one possible avenue for developing computers that supersede the limitations of today’s chips, which are essentially based on the same principles as chips from the earliest days of the computing revolution in the 1960s.

In a paper in Nature Photonics, Engheta’s group, together with that of Firooz Aflatouni, Associate Professor in Electrical and Systems Engineering, describes the development of the new chip. “We decided to join forces,” says Engheta, leveraging the fact that Aflatouni’s research group has pioneered nanoscale silicon devices.

Their goal was to develop a platform for performing what is known as vector-matrix multiplication, a core mathematical operation in the development and function of neural networks, the computer architecture that powers today’s AI tools.

Read the full story in Penn Engineering Today.

Nader Engheta is the H. Nedwill Ramsey Professor in Electrical and Systems Engineering, Bioengineering, Materials Science and Engineering, and in Physics and Astronomy.

Penn Scientists Reflect on One Year of ChatGPT

by Erica Moser

René Vidal, at the podium, introduces the event “ChatGPT turns one: How is generative AI reshaping science?” Bhuvnesh Jain, left at the table, moderated the discussion with Sudeep Bhatia, Konrad Kording, Andrew Zahrt, and Nick Pangakis.

As a neuroscientist surveying the landscape of generative AI—artificial intelligence capable of generating text, images, or other media—Konrad Kording cites two potential directions forward: One is the “weird future” of political use and manipulation, and the other is the “power tool direction,” where people use ChatGPT to get information as they would use a drill to build furniture.

“I’m not sure which of those two directions we’re going but I think a lot of the AI people are working to move us into the power tool direction,” says Kording, a Penn Integrates Knowledge (PIK) University professor with appointments in the Perelman School of Medicine and School of Engineering and Applied Science. Reflecting on how generative AI is shifting the paradigm of science as a discipline, Kording said he thinks “it will push science as a whole into a much more collaborative direction,” though he has concerns about ChatGPT’s blind spots.

Kording joined three University of Pennsylvania researchers from the chemistry, political science, and psychology departments sharing their perspectives in the recent panel “ChatGPT turns one: How is generative AI reshaping science?” PIK Professor René Vidal opened the event, which was hosted by the School of Arts & Sciences’ Data Driven Discovery Initiative (DDDI), and Bhuvnesh Jain, physics and astronomy professor and co-faculty director of DDDI, moderated the discussion.

“Generative AI is moving so rapidly that even if it’s a snapshot, it will be very interesting for all of us to get that snapshot from these wonderful experts,” Jain said. OpenAI launched ChatGPT, a large language model (LLM)-based chatbot, on Nov. 30, 2022, and it rapidly ascended to ubiquity in news reports, faculty discussions, and research papers. Colin Twomey, interim executive director of DDDI, told Penn Today that it’s an open question as to how it will change the landscape of scientific research, and the` idea of the event was to solicit colleagues’ opinions on interesting directions in their fields.

Read the full story in Penn Today.

Konrad Paul Kording is Nathan Francis Mossell University Professor in Bioengineering and Computer and Information Science in Penn Engineering and in Neuroscience in the Perelman School of Medicine.

On a Different Wavelength, Nader Engheta Leads a Community in Light

Nader Engheta was puzzled when he got a call from the psychology department about a fish.
In the early 1990s, Engheta, a newly minted associate professor of electrical engineering in Penn’s School of Engineering and Applied Science, was a respected expert in radio wave technologies. But in recent years, his work had been expanding into subjects at once more eccentric and fundamental.

Nader Engheta was puzzled when he got a call from the psychology department about a fish.

In the early 1990s, Engheta, a newly minted associate professor of electrical engineering in Penn’s School of Engineering and Applied Science, was a respected expert in radio wave technologies. But in recent years, his work had been expanding into subjects at once more eccentric and fundamental.

Engheta’s interest in electromagnetic waves was not limited to radio frequencies, as a spate of fresh publications could attest. Some studies investigated a range of wave interactions with a class of matter known as a “chiral media,” materials with molecular configurations that exhibit qualities of left or right “handedness.” Others established practical electromagnetic applications for a bewildering branch of mathematics called “fractional calculus,” an area with the same Newtonian roots as calculus proper but a premise as eyebrow-raising as the suggestion a family might literally include two-and-a-half children.

Electromagnetic waves are organized on a spectrum of wavelengths. On the shorter end of the spectrum are high-energy waves, such as X-rays. In the middle, there is the limited range we see as visible light. And on the longer end are the lower-energy regimes of radio and heat.

Researchers tend to focus on one kind of wave or one section of the spectrum, exploring quirks and functions unique to each. But all waves, electromagnetic or not, share the same characteristics: They consist of a repeating pattern with a certain height (amplitude), rate of vibration (frequency), and distance between peaks (wavelength). These qualities can define a laser beam, a broadcasting voice, a wind-swept lake, or a violin string.

Engheta has never been the kind of scholar to limit the scope of his curiosity to a single field of research. He is interested in waves, and his fascination lies equally in the physics that determine wave behavior and the experimental technologies that push the boundaries of those laws.

So, when Edward Pugh, a mathematical psychologist studying the physiology of visual perception, explained that green sunfish might possess an evolutionary advantage for seeing underwater, Engheta listened.

Soon, the two Penn professors were pouring over microscope images of green sunfish retinas.

Read Devorah Fischler’s full story about Nader Engheta and watch an accompanying video at Penn Today.

Nader Engheta is H. Nedwill Ramsey Professor of Electrical and Systems Engineering at Penn Engineering, with secondary appointments in the departments of Bioengineering, Materials Science and Engineering, and Physics and Astronomy in the School of Arts & Sciences.

Franklin Medal Laureate Nader Engheta Honored at Sculpting Waves Symposium

by

(Left to Right) Vijay Kumar, Nemirovsky Family Dean of Penn Engineering, Nader Engheta, H. Nedwill Ramsey Professor in Electrical and Systems Engineering, and Michele Marcolongo, Drosdick Endowed Dean of Villanova University’s College of Engineering

On April 26, scholars from all over the world gathered at Villanova University to celebrate extraordinary innovation in the physics and technology of light.

The Franklin Institute Awards Laureate Symposium honored Nader Engheta, H. Nedwill Ramsey Professor in Electrical and Systems Engineering, Bioengineering, Materials Science and Engineering in the School of Engineering and Applied Science and in Physics and Astronomy in the College of Arts & Sciences at the University of Pennsylvania . The event heralded the awards gala held on April 27, where Engheta received the Benjamin Franklin Medal in Electrical Engineering from the Franklin Institute in Philadelphia, Pennsylvania.

The symposium, titled “Sculpting Waves with Complex Materials,” explored the richness and breadth of Engheta’s impact.

In a glass-paneled lecture hall nestled between flowering dogwoods and limber pines, speakers attested to Engheta’s technical acumen and intellectual creativity, describing his pathbreaking work in light-matter interaction.

Andrea Alù, Distinguished Professor at the City University of New York, Einstein Professor of Physics at the Graduate Center, CUNY and former Penn Engineering postdoctoral fellow, cited Engheta as “one of the original pioneers of the field of complex electromagnetic structures and modern metamaterials,” and the “father” of four influential fields: analog computing with metamaterials, plasmonic cloaking, non-zero-index metamaterials and optical nanocircuits.

Read the full story in Penn Engineering Today.

Watch the recording of the 2023 Franklin Institute Awards Ceremony on the Institute’s Youtube page.

2023 Solomon R. Pollack Awards for Excellence in Graduate Bioengineering Research

The Solomon R. Pollack Award for Excellence in Graduate Bioengineering Research is given annually to the most deserving Bioengineering graduate students who have successfully completed research that is original and recognized as being at the forefront of their field. This year, the Department of Bioengineering at the University of Pennsylvania recognizes the stellar work of four graduate students in Bioengineering.

Margaret Billingsley

Dissertation: “Ionizable Lipid Nanoparticles for mRNA CAR T Cell Engineering”

Maggie Billingsley

Margaret earned a bachelor’s degree in Biomedical Engineering from the University of Delaware where she conducted research in the Day Lab on the use of antibody-coated gold nanoparticles for the detection of circulating tumor cells. She conducted doctoral research in the lab of Michael J. Mitchell, J. and Peter Skirkanich Assistant Professor in Bioengineering. After defending her thesis at Penn in 2022, Margaret began postdoctoral training at the Massachusetts Institute of Technology (MIT) in the Hammond Lab where she is investigating the design and application of polymeric nanoparticles for combination therapies in ovarian cancer. She plans to use these experiences to continue a research career focused on drug delivery systems.

“Maggie was an absolutely prolific Ph.D. student in my lab, who pioneered the development of new mRNA lipid nanoparticle technology to engineer the immune system to target and kill tumor cells,” says Mitchell. “Maggie is incredibly well deserving of this honor, and I am so excited to see what she accomplishes next as a Postdoctoral Fellow at MIT and ultimately as a professor running her own independent laboratory at a top academic institution.”

Victoria Muir

Dissertation: “Designing Hyaluronic Acid Granular Hydrogels for Biomaterials Applications”

Victoria Muir

Victoria is currently a Princeton University Presidential Postdoctoral Research Fellow in the lab of Sujit S. Datta, where she studies microbial community behavior in 3D environments. She obtained her Ph.D. in 2022 as an NSF Graduate Research Fellow at Penn Bioengineering under the advisement of Jason A. Burdick, Adjunct Professor in Bioengineering at Penn and Bowman Endowed Professor in Chemical and Biological Engineering at the University of Colorado, Boulder. She received a B.ChE. in Chemical Engineering from the University of Delaware in 2018 as a Eugene DuPont Scholar. Outside of research, Victoria is highly active in volunteer and leadership roles within the American Institute of Chemical Engineers (AIChE), currently serving as Past Chair of the Young Professionals Community and a member of the Career and Education Operating Council (CEOC). Victoria’s career aspiration is to become a professor of chemical engineering and to lead a research program at the interaction of biomaterials, soft matter, and microbiology.

“Victoria was a fantastic Ph.D. student,” says Burdick. “She worked on important projects related to granular materials from the fundamentals to applications in tissue repair. She was also a leader in outreach activities, a great mentor to numerous undergraduates, and is already interviewing towards an independent academic position.”

Sadhana Ravikumar 

Dissertation: “Characterizing Medial Temporal Lobe Neurodegeneration Due to Tau Pathology in Alzheimer’s Disease Using Postmortem Imaging”

Sadhana Ravikumar

Sadhana completed her B.S. in Electrical Engineering at the University of Cape Town, South Africa in 2014 and her M.S. in Biomedical Engineering from Carnegie Mellon University in 2017. Outside of the lab, she enjoys spending time in nature and exploring restaurants in Philadelphia with friends. She focused her doctoral work on the development of computational image analysis techniques applied to ex vivo human brain imaging data in the Penn Image Computing and Science Laboratory of Paul Yushkevich, Professor of Radiology at the Perelman School of Medicine and member of the Penn Bioengineering Graduate Group. She hopes to continue working at the intersection of machine learning and biomedical imaging to advance personalized healthcare and drug development.

“Dr. Sadhana Ravikumar’s Ph.D. work is a tour de force that combines novel methodological contributions crafted to address the challenge of anatomical variability in ultra-high resolution ex vivo human brain MRI with new clinical knowledge on the contributions of molecular pathology to neurodegeneration in Alzheimer’s disease,” says Yushkevich. “I am thrilled that this excellent contribution, as well as Sadhana’s professionalism and commitment to mentorship, have been recognized through the Sol Pollack award.”

Hannah Zlotnick

Dissertation: “Remote Force Guided Assembly of Complex Orthopaedic Tissues”

Hannah Zlotnick

Hannah was a Ph.D. candidate in the lab of Robert Mauck, Mary Black Ralston Professor in Orthopaedic Surgery and in Bioengineering. She successfully defended her thesis and graduated in August 2022. During her Ph.D., Hannah advanced the state-of-the-art in articular cartilage repair by harnessing remote fields, such as magnetism and gravity. Using these non-invasive forces, she was able to control cell positioning within engineered tissues, similar to the cell patterns within native cartilage, and enhance the integration between cartilage and bone. Her work could be used in many tissue engineering applications to recreate complex tissues and tissue interfaces. Hannah earned a B.S. in Biological Engineering from the Massachusetts Institute of Technology (MIT) in 2017 during which time she was also a member of the women’s varsity soccer team. At Penn, Hannah was also involved in the Graduate Association of Bioengineers (GABE) intramurals & leadership, and helped jumpstart the McKay DEI committee. Since completing her Ph.D., Hannah has begun her postdoctoral research as a Schmidt Science Fellow in Jason Burdick’s lab at the University of Colorado Boulder where she looks to improve in vitro disease models for osteoarthritis.

“Hannah was an outstanding graduate student, embodying all that is amazing about Penn BE – smart, driven, inventive and outstanding in every way,” says Mauck. “ I can’t wait to see where she goes and what she accomplishes!”

Congratulations to our four amazing 2023 Sol Pollack Award winners!

Engheta, Margulies Elected to the American Academy of Arts & Sciences

Two faculty affiliated with the Department of Bioengineering at the University of Pennsylvania have been elected to the American Academy of Arts & Sciences. They join nearly 270 new members honored in 2023, recognized for their excellence, innovation, leadership, and broad array of accomplishments.

Nader Engheta
Nader Engheta, the H. Nedwill Ramsey Professor.

Nader Engheta is the H. Nedwill Ramsey Professor, with affiliations in the departments of Electrical and Systems Engineering (primary appointment), Bioengineering (secondary appointment) and Materials Science and Engineering (secondary appointment) in the School of Engineering and Applied Science; and Physics and Astronomy (secondary appointment) in the School of Arts & Sciences. His current research activities span a broad range of areas including optics, photonics, metamaterials, electrodynamics, microwaves, nano-optics, graphene photonics, imaging and sensing inspired by eyes of animal species, microwave and optical antennas, and physics and engineering of fields and waves. He has received numerous awards for his research, including the 2023 Benjamin Franklin Medal in Electrical Engineering, the 2020 Isaac Newton Medal and Prize from the Institute of Physics (U.K.), the 2020 Max Born Award from OPTICA (formerly OSA), induction to the Canadian Academy of Engineering as an International Fellow (2019), U.S. National Academy of Inventors (2015), and the Ellis Island Medal of Honor from the Ellis Island Honors Society (2019). He joins four other Penn faculty elected to the Academy this year.

Read the announcement and the full list of Penn electees in Penn Today.

Susan Margulies, Ph.D. (Photo: Jack Kearse)

Susan Margulies, Professor in the Wallace H. Coulter Department of Biomedical Engineering in the College of Engineering at Georgia Tech, was also elected. Margulies is both Professor Emeritus in Penn Bioengineering and an alumna of the program, having earned her Ph.D. with the department in 1987. Margulies is an expert in pediatric traumatic brain injury and lung injury. She previously served as Chair of Biomedical Engineering at Georgia Tech/Emory University and in 2021 became the first biomedical engineer selected to lead the National Science Foundation’s (NSF) Directorate of Engineering.

Read the announcement of Margulies’ elected to the Academy at Georgia Tech.

This Patterned Surface Solves Equations at the Speed of Light

by Devorah Fischler

A tailored silicon nanopattern coupled with a semi-transparent gold mirror can solve a complex mathematical equation using light. (Image credit: Ella Maru studio)

Researchers at the University of Pennsylvania, AMOLF, and the City University of New York (CUNY) have created a surface with a nanostructure capable of solving mathematical equations.

Powered by light and free of electronics, this discovery introduces exciting new prospects for the future of computing.

Nader Engheta, H. Nedwill Ramsey Professor of Electrical and Systems Engineering at the University of Pennsylvania School of Engineering and Applied Science, is a visionary figure in optics and in electromagnetic platforms. For the last two decades, he has created theory and designed experiments to make electromagnetic and optical devices that operate at the fastest rate in the universe.

Engheta is the founder of the influential field of “optical metatronics.” He creates materials that interact with photons to manipulate data at the speed of light. Engheta’s contribution to this study marks an important advance in his quest to use light-matter interactions to surpass the speed and energy limitations of digital electronics, bringing analog computing out of the past and into the future.

“I began the work on optical metatronics in 2005,” says Engheta, “wondering if it were possible to recreate the elements of a standard electronic circuit at nanoscale. At this tiny size, it would be possible to manipulate the circuit with light, rather than electricity. After achieving this, we became more ambitious, envisioning collections of these nanocircuits as processors. In 2014, we were designing materials that used these optical nanostructures to perform mathematical operations, and in 2019, we anted up to entire mathematical equations using microwaves. Now, my collaborators and I have created a surface that can solve equations using light waves, a significant step closer to our larger goals for computing materials.”

The study, recently published in Nature Nanotechnology, demonstrates the possibility of solving complex mathematical problems and a generic matrix inversion at speeds far beyond those of typical digital computing methods.

The solution converges in about 349 femtoseconds (less than one trillionth of a second), orders of magnitude faster than the clock speed of a conventional processor.

Read the full story in Penn Engineering Today.

Nader Engheta is the H. Nedwill Ramsey Professor in the Departments of Electrical and Systems Engineering and in Bioengineering in the School of Engineering and Applied Science and Professor in Physics and Astronomy in the School of Arts & Sciences at the University of Pennsylvania.

Through the Lens: A Digital Depiction of Dyslexia

by Nathi Magubane

Artist-in-residence and visiting scholar Rebecca Kamen has blended AI and art to produce animated illustrations representing how a dyslexic brain interprets information.

A collage of artwork depicts a series of abstract visualizations of networks.
A work that Penn artist-in-residence Rebecca Kamen produced for the show, “Dyslexic Dictionary” at Arion Press in San Francisco. Here, she reinterprets Ph.D. candidate Dale Zhou’s network visualization. (Image: Cat Fennell)

Communicating thoughts with words is considered a uniquely human evolutionary adaptation known as language processing. Fundamentally, it is an information exchange, a lot like data transfer between devices, but one riddled with discrete layers of complexity, as the ways in which our brains interpret and express ideas differ from person to person.

Learning challenges such as dyslexia are underpinned by these differences in language processing and can be characterized by difficulty learning and decoding information from written text.

Artist-in-residence in Penn’s Department of Physics and Astronomy Rebecca Kamen has explored her personal relationship with dyslexia and information exchange to produce works that reflect elements of both her creative process and understanding of language. Kamen unveiled her latest exhibit at Arion Press Gallery in San Francisco, where nine artists with dyslexia were invited to produce imaginative interpretations of learning and experiencing language.

The artists were presented with several prompts in varying formats, including books, words, poems, quotes, articles, and even a single letter, and tasked with creating a dyslexic dictionary: an exploration of the ways in which their dyslexia empowered them to engage in information exchange in unique ways.

Undiagnosed dyslexia

“[For the exhibit], each artist selected a word representing the way they learn, and mine was ‘lens,’” explains Kamen. “It’s a word that captures how being dyslexic provides me with a unique perspective for viewing and interacting with the world.”

From an early age, Kamen enjoyed learning about the natural sciences and was excited about the process of discovery. She struggled, however, with reading at school, which initially presented an obstacle to achieving her dreams of becoming a teacher. “I had a difficult time getting into college,” says Kamen. “When I graduated high school, the word ‘dyslexia’ didn’t really exist, so I assumed everyone struggled with reading.”

Kamen was diagnosed with dyslexia well into her tenure as a professor. “Most dyslexic people face challenges that may go unnoticed by others,” she says, “but they usually find creative ways to overcome them.”

This perspective on seeing and experiencing the world through the lens of dyslexia not only informed Kamen’s latest work for the exhibition “Dyslexic Dictionary,” but also showcased her background in merging art and science. For decades, Kamen’s work has investigated the intersection of the two, creating distinct ways of exploring new relationships and similarities.

“Artists and scientists are curious creatures always looking for patterns,” explains Kamen. “And that’s because patterns communicate larger insights about the world around us.”

Creativity and curiosity

This idea of curiosity and the patterns its neural representations could generate motivated “Reveal: The Art of Reimagining Scientific Discovery,” Kamen’s previous exhibit, which was inspired by the work of Penn professor Dani Bassett, assistant professor David Lydon-Staley and American University associate professor Perry Zurn on the psychological and historical-philosophical basis of curiosity.

The researchers studied different information-seeking approaches by monitoring how participants explore Wikipedia pages and categorically related these to two ideas rooted in philosophical understandings of learning: a “busybody,” who typically jumps between diverse ideas and collects loosely connected information; and a more purpose-driven “hunter,” who systematically ties in closely related concepts to fill their knowledge gaps.

They used these classifications to inform their computational model, the knowledge network. This uses text and context to determine the degree of relatedness between the Wikipedia pages and their content—represented by dots connected with lines of varying thickness to illustrate the strength of association.

In an adaption of the knowledge network, Kamen was classified as a dancer, an archetype elaborated on in an accompanying review paper by Dale Zhou, a Ph.D. candidate in Bassett’s Complex Systems Lab, who had also collaborated with Kamen on “Reveal.”

“The dancer can be described as an individual that breaks away from the traditional pathways of investigation,” says Zhou. “Someone who takes leaps of creative imagination and in the process, produces new concepts and radically remodels knowledge networks.”

Read the full story in Penn Today.

Rebecca Kamen is a visiting scholar and artist-in-residence in the Department of Physics & Astronomy in Penn’s School of Arts & Sciences.

Dale Zhou is a Ph.D. candidate in Penn’s Neuroscience Graduate Group.

Dani Smith Bassett is J. Peter Skirkanich Professor in Bioengineering with secondary appointments in the Departments of Physics & Astronomy, Electrical & Systems Engineering, Neurology, and Psychiatry.

David Lydon-Staley is an Assistant Professor in the Annenberg School for Communications and Bioengineering and is an alumnus of the Bassett Lab.

 

Penn Scientist Nader Engheta Wins the Benjamin Franklin Medal

Nader Engheta
Nader Engheta (Image: Felice Macera)

by Amanda Mott

University of Pennsylvania scientist Nader Engheta has been selected as a 2023 recipient of the Benjamin Franklin Medal, one of the world’s oldest science and technology awards. The laureates will be honored on April 27 at a ceremony at the Franklin Institute in Philadelphia.

Engheta, H. Nedwill Ramsey Professor in Electrical and Systems Engineering, is among nine outstanding individuals recognized with Benjamin Franklin Medals this year for their achievements in extraordinary scientific, engineering and business leadership.

“As a scientist and a Philadelphian, I am deeply honored and humbled to receive the Franklin Medal. It is the highest compliment to receive an award whose past recipients include some of my scientific heroes such as Albert Einstein, Nikola Tesla, Alexander Graham Bell, and Max Planck. I am very thankful to the Franklin Institute for bestowing this honor upon me.”

Larry Dubinski, President and CEO of The Franklin Institute, says, “We are proud to continue The Franklin Institute’s longtime legacy of recognizing individuals for their contributions to humanity. These extraordinary advancements in areas of such importance as social equity, sustainability, and safety are significantly moving the needle in the direction of positive change and therefore laying the groundwork for a remarkable future.”

The 2023 Benjamin Franklin Medal in Electrical Engineering goes to Engheta for his transformative innovations in engineering novel materials that interact with electromagnetic waves in unprecedented ways, with broad applications in ultrafast computing and communication technologies.

“Professor Engheta’s pioneering work in metamaterials and nano-optics points the way to new and truly revolutionary computing capabilities in the future,” says University of Pennsylvania President Liz Magill. “Penn inaugurated the age of computers by creating the world’s first programmable digital computer in 1945. Professor Engheta’s work continues this tradition of groundbreaking research and discovery that will transform tomorrow. We are thrilled to see him receive the recognition of the Benjamin Franklin Medal.”

Engheta founded the field of optical nanocircuits (“optical metatronics”), which merges nanoelectronics and nanophotonics. He is also known for establishing and& developing the field of near-zero-index optics and epsilon-near-zero (ENZ) materials with near-zero electric permittivity. Through his work he has opened many new frontiers, including optical computation at the nanoscale and scattering control for cloaking and transparency. His work has far-reaching implications in various branches of electrical engineering, materials science, optics, microwaves, and quantum electrodynamics.

“This award recognizes Dr. Engheta’s trailblazing advances in engineering and physics,” says Vijay Kumar, Nemirovsky Family Dean of Penn Engineering.“ The swift and sustainable technologies his research in metamaterials and metatronics offers the world are the result of a lifelong commitment to scientific curiosity. For over 35 years, Nader Engheta has personified Penn Engineering’s mission of inventing the future.”

Nader Engheta is the H. Nedwill Ramsey Professor in the Departments of Electrical and Systems Engineering and Bioengineering in the School of Engineering and Applied Science and professor of physics and astronomy in the School of Arts & Sciences at the University of Pennsylvania.

This story originally appeared in Penn Today.

ASSET Center Inaugural Seed Grants Will Fund Trustworthy AI Research in Healthcare

by

Illustration credit: Melissa Pappas

Penn Engineering’s newly established ASSET Center aims to make AI-enabled systems more “safe, explainable and trustworthy” by studying the fundamentals of the artificial neural networks that organize and interpret data to solve problems.

ASSET’s first funding collaboration is with Penn’s Perelman School of Medicine (PSOM) and the Penn Institute for Biomedical Informatics (IBI). Together, they have launched a series of seed grants that will fund research at the intersection of AI and healthcare.

Teams featuring faculty members from Penn Engineering, Penn Medicine and the Wharton School applied for these grants, to be funded annually at $100,000. A committee consisting of faculty from both Penn Engineering and PSOM evaluated 18 applications and  judged the proposals based on clinical relevance, AI foundations and potential for impact.

Artificial intelligence and machine learning promise to revolutionize nearly every field, sifting through massive amounts of data to find insights that humans would miss, making faster and more accurate decisions and predictions as a result.

Applying those insights to healthcare could yield life-saving benefits. For example, AI-enabled systems could analyze medical imaging for hard-to-spot tumors, collate multiple streams of disparate patient information for faster diagnoses or more accurately predict the course of disease.

Given the stakes, however, understanding exactly how these technologies arrive at their conclusions is critical. Doctors, nurses and other healthcare providers won’t use such technologies if they don’t trust that their internal logic is sound.

“We are developing techniques that will allow AI-based decision systems to provide both quantifiable guarantees and explanations of their predictions,” says Rajeev Alur, Zisman Family Professor in Computer and Information Science and Director of the ASSET Center. “Transparency and accuracy are key.”

“Development of explainable and trustworthy AI is critical for adoption in the practice of medicine,” adds Marylyn Ritchie, Professor of Genetics and Director of the Penn Institute for Biomedical Informatics. “We are thrilled about this partnership between ASSET and IBI to fund these innovative and exciting projects.”

 Seven projects were selected in the inaugural class, including projects from Dani S. Bassett, J. Peter Skirkanich Professor in the Departments of Bioengineering, Electrical and Systems Engineering, Physics & Astronomy, Neurology, and Psychiatry, and several members of the Penn Bioengineering Graduate Group: Despina Kontos, Matthew J. Wilson Professor of Research Radiology II, Department of Radiology, Penn Medicine and Lyle Ungar, Professor, Department of Computer and Information Science, Penn Engineering; Spyridon Bakas, Assistant Professor, Departments of Pathology and Laboratory Medicine and Radiology, Penn Medicine; and Walter R. Witschey, Associate Professor, Department of Radiology, Penn Medicine.

Optimizing clinical monitoring for delivery room resuscitation using novel interpretable AI

Elizabeth Foglia, Associate Professor, Department of Pediatrics, Penn Medicine and the Children’s Hospital of Philadelphia

Dani S. Bassett, J. Peter Skirkanich Professor, Departments of Bioengineering and Electrical and Systems Engineering, Penn Engineering

 This project will apply a novel interpretable machine learning approach, known as the Distributed Information Bottleneck, to solve pressing problems in identifying and displaying critical information during time-sensitive clinical encounters. This project will develop a framework for the optimal integration of information from multiple physiologic measures that are continuously monitored during delivery room resuscitation. The team’s immediate goal is to detect and display key target respiratory parameters during delivery room resuscitation to prevent acute and chronic lung injury for preterm infants. Because this approach is generalizable to any setting in which complex relations between information-rich variables are predictive of health outcomes, the project will lay the groundwork for future applications to other clinical scenarios.

Read the full list of projects and abstracts in Penn Engineering Today.