Inventing the Future
Rethinking the Computer Chip in the Age of AI
When dealing with the enormous amounts of data essential for machine learning and AI applications, the latency produced by the transfer of data from storage to processing can cause major challenges. A team of researchers, co-led by Deep Jariwala, Asst. Prof. in ESE, have introduced a transistor-free compute-in-memory architecture that permits 3 computational tasks essential for AI applications: search, storage, and neural network operations.
Algorithm for 2D-to-3D Engineering Integrates Art, Nature and Science
The algorithm developers, led by Shu Yang, Joseph Bordogna Professor and Chair of the Department of Materials Science and Engineering, take inspiration from the East Asian paper-cutting art of kirigami to create a mathematically sound method of cutting and stacking flat materials into durable curved objects. The algorithm is the subject of a recent study in Science Advances.
Y-Prize 2022-2023: Solar Powered Aerial Vehicles & Physics-Informed Neural Networks
This year’s Y-Prize Competition student teams will use either “Solar Powered Aerial Vehicles” to create lift without moving parts, or “Physics-Informed Neural Networks” algorithms that can use physical principles to infer unknowns. Teams enter the competition by pitching a real-world problem and product based on the capabilities of one of these technologies.
Tunneling Electrons Confirm New Device Structure for Energy-Efficient Chips
The Jariwala Lab TFET design, created by Deep Jariwala, Assistant Professor in the Department of Electrical and Systems Engineering, and team, is a field-effect transistor that relies on a physical property known as tunneling. The design reduces the amount of voltage needed for switching in commercial computing chips by half. The new logic device design is the subject of a recently published study in Nature Electronics.
PSOC Seminar: “Mechanical waves identify the amputation position during wound healing in the amputated zebrafish tailfin” (Keng-hui Lin, Institute of Physics)
MEAM Seminar: “The Challenges and Opportunities of Battery-Powered Flight”
CIS Grace Hopper Lecture: “Data Privacy is Important, But It’s Not Enough”