Join the rest of the Pratt School of Engineering Community in a special dedication of a special new place on our campus -- the Thomas E. Harrington E'66 GREAT IDEAS BENCH. The dedication will take place at the BENCH, located where Hudson Hall meets Harrington Engineering Quad.
Abstract Neuro-symbolic AI presents tremendous opportunities for more efficient foundation models in the form of integrating classical symbolic methods with deep learning. However, that integration is faced with several key challenges, including the correspondence between symbolic and neural systems and the scale of modern AI models. In this talk, we cover some of these challenges […]
Join Duke's Pratt School of Engineering during this week-long event celebrating how engineers make a difference in our world. More at pratt.duke.edu/e-week
Artificial intelligence and machine learning have become important components of the computational toolbox that can be used to advance chemical research and discovery. Our group has been working on advancing AI/ML as it applies to the broad subfields of synthetic organic chemistry (for developing/discovering reactions), medicinal chemistry (for developing/discovering new functional molecules), and analytical chemistry […]
Abstract: During cardiovascular development, peristaltic contraction of the embryonic heart tube produces time-varying hemodynamic forces and pressure gradients across the atrioventricular canal. However, the relative importance of myocardial contraction and hemodynamic force to modulate cardiovascular morphogenesis in the non-Newtonian flow regime remains poorly understood. By developing the 4-D light-sheet fluorescent microscope and post-imaging machine-learning algorithms, […]
From autonomous vehicles navigating busy intersections to quadrupeds deployed in household environments, robots must operate safely and efficiently around people in uncertain and unstructured situations. However, today's robots still struggle to robustly handle low-probability events without becoming overly conservative. In this talk, I will discuss how planning in the joint space of physical and information […]
Preventing injury and restoring mobility following injury, both musculoskeletal and neuromuscular, is challenging. In recent years, the fields of biomechanics and clinical rehabilitation have informed the development of wearable devices and assessment tools that aid in rehabilitation and in maintaining mobility. Wearable exosystems are assistive devices that can target weakness in a specific joint or […]
Robots are traditionally designed with fixed physical hardware and control policies that make them specialized for repetitive tasks and structured environments. This talk discusses foundational work toward robots that "evolve on demand," morphing their bodies and adapting their behaviors to accommodate multiple tasks in diverse environments. First, I will introduce robotic structures made from stiffness-changing […]
Efficient and resilient coordination among autonomous agents plays an important role in various domains such as energy management, robotic swarms, autonomous vehicles and beyond. As these systems grow in complexity and scale, the challenge of achieving optimal coordination becomes increasingly difficult. The first part of the talk will focus on tackling scalability issues by leveraging […]
Sepsis, a life-threatening syndrome arising from a dysregulated host response to infection, exhibits significant heterogeneity in clinical presentation and outcome. This complexity underscores the need for refined stratification strategies beyond traditional clinical parameters. This presentation will explore how the integration of multi-omic data (e.g., genomics, transcriptomics, proteomics, metabolomics) can be leveraged to identify distinct sepsis […]
