ABSTRACT:
Deep learning models, despite their power, lag behind the biological brain in interpretability, energy efficiency, and physical plausibility. This presentation explores the mathematical design principles of biological neural circuits -- building upon the classic concept that neural activity is fundamentally driven by…
ABSTRACT:
As the Deputy Director for Innovation and Emerging Technologies at the California Governor’s Office of Business and Economic Development (GO-Biz), Tre Bradley is the primary advisor to California state leaders on technology trends and opportunities, focusing on commercialization, technology transfer, and talent pipeline…
ABSTRACT:
We seek the ability to take a few images of a scene of interest, and turn it into an immersive visual experience, where one can explore it from different viewpoints, in effect visualizing a 3D representation of an object, scene or photograph, and providing numerous applications in augmented reality, e-commerce and 3D…
ABSTRACT:
The experimental sciences have long relied on labor-intensive, manual workflows that limit scalability and slow the pace of research and discovery. Despite advances in instrumentation and data analysis, the act of performing physical experiments remains time-consuming and resource- intensive, ultimately limiting the…
ABSTRACT:
The convergence of artificial intelligence and programmable optics is opening new opportunities for both biological imaging and optical machine learning. By shifting complexity from optical hardware to data-driven algorithms and reconfigurable systems, these approaches promise faster, more adaptive, and more efficient…
ABSTRACT:
Humans are highly susceptible to framing manipulations in intertemporal decision making—choices that involve tradeoffs between immediate and delayed rewards. Classic biases such as the magnitude effect, in which larger reward amounts increase patience, have been attributed to self-control, reward system activation, and…
ABSTRACT:
Modern deep learning is exceptionally good at seeing patterns, but it often sees too much. As models scale, they increasingly begin to see “ghosts", which are nuisance factors that haunt the data and masquerade as true signals. These ghosts appear as stereotypes in social data, as overwhelming thermal emission in…
ABSTRACT:
Continuous-domain signals, curves, and trajectories sampled over time or space—arise routinely in modern sensing, health, and human–computer interaction applications. Such a type of data is also called Functional data in the statistical literature. Despite their prevalence, providing reliable uncertainty quantification…
ABSTRACT:
Autonomous systems are rapidly moving from research labs into the real world, powering drones, self-driving cars, and service robots. Yet, their widespread adoption hinges not only on performance, but on assurance—the ability to guarantee that robots do what they are intended to do, safely and reliably, even under…
ABSTRACT:
The revolutionary capabilities of AI with machine learning have enabled an increasingly broad range of applications, which has brought many new challenges in ensuring the trustworthiness of AI applications. In this talk, I will present our research on trustworthy AI with verifiable guarantees. I will first introduce our…