Physics-Motivated and Inspired Probabilistic Learning
Published: | 3:15 pm | Posted in: Events
Speaker: Shibo Li Date: Apr 1, 11:45am–12:45pm Abstract: AI has emerged as the most transformative and revolutionary technique, reshaping many aspects of our lives. Its intersection with science, particularly physics, has opened new avenues for understanding our world and universe. This understanding is grounded in centuries of exploration by brilliant minds. Physics studies today predominantly […]
The Power of Opening the Black Box of Deep Learning
Published: | 2:54 pm | Posted in: Events
Speaker: Chaoyue Liu Date: Mar 29, 11:45am–12:45pm Abstract: We are now observing an ongoing “AI spring” powered by the emergence and successful implementation of deep neural network models. However, neural networks are often considered as black box models lacking a theoretical and fundamental understanding, leaving deep learning mostly driven by heuristics, not interpretable and not […]
Data-Efficiency and Robustness in Machine Learning
Published: | 3:25 pm | Posted in: Events
Speaker: Shiwei Zeng Date: Mar 27, 11:45am–12:45pm Abstract: Machine learning has been a powerful tool in the modern world. In the past decades, due to the explosion of unverified data sources, and the increasing interaction between human and computer, it is of concern whether machine learning algorithms are robust to data corruption or even adversarial […]
Learning to Synthesize Images with Multimodal and Hierarchical Inputs
Published: | 1:46 pm | Posted in: Events
Speaker: Yu Zeng Date: Mar 25, 11:45am–12:45pm Abstract: In recent years, the field of image synthesis and manipulation has experienced remarkable advancements driven by the success of deep learning methods and the availability of Web-scale datasets. Despite this progress, most current approaches predominantly rely on generating images based on simplistic inputs such as text and […]
Achieving Compositional Safety and Security in IoT Environments
Published: | 2:55 pm | Posted in: Events
Speaker: Muslum Ozgur Ozmen Date: Mar 8, 11:45am–12:45pm Abstract: The Internet of Things (IoT) systems include sensors that measure the physical world, actuators that influence it, and IoT apps that automate these sensors and actuators. While IoT environments have revolutionized our lives by integrating digital connectivity into physical processes, they have also become attractive targets […]
Ensuring Policy and Privacy Compliance of Voice Personal Assistant Applications
Published: | 1:18 pm | Posted in: Events
Speaker: Song Liao Date: Mar 6, 11:45am–12:45pm Abstract: Voice personal assistants (VPAs) such as Amazon Alexa and Google Assistant are rapidly gaining popularity in both domestic and business. Today’s VPA services have been largely expanded by allowing third-party developers to build voice apps (named “skill” in the Amazon Alexa platform) and publish them to marketplaces. […]
Collaborative IoT Communications, Networking and Beyond
Published: | 1:29 pm | Posted in: Events
Speaker: Xin Liu Date: Mar 5, 11:45am–12:45pm Abstract: The rapid expansion of IoT technology is revolutionizing a wide array of applications, from smart homes and transportation to logistics, significantly enhancing our daily life quality. By 2030, it is projected that each individual will interact with between 300 to 500 IoT devices daily. However, enabling seamless […]
Trustworthy Systems from Secure Computation and Verification
Published: | 3:15 pm | Posted in: Events
Speaker: Chenkai Weng Date: Mar 4, 11:45am–12:45pm Abstract: With the advancement of digital globalization and the enhancement of privacy regulations, a conflict between centralized computing and distributed information is emerging. It becomes increasingly important to verify or compute distributed information while protecting privacy and integrity. In this talk, I will first introduce my research that […]
Causal Machine Learning: Continuous Structure Learning and Identifiability of Causal Invariances
Published: | 9:31 pm | Posted in: Events
Speaker: Kevin Bello Date: Mar 1, 11:45am–12:45pm Abstract: Interpretability and causality are key desiderata in modern machine learning systems. Graphical models, and more specifically directed acyclic graphs (DAGs, a.k.a. Bayesian networks), serve as a well-established tool for expressing interpretable causal relationships. However, the task of estimating DAG structures from data poses a significant challenge, given […]
Securing Embedded Systems Using Compartmentalization
Published: | 4:16 pm | Posted in: Events
Speaker: Arslan Khan Date: Feb 29, 11:45am–12:45pm Abstract: Embedded systems are low-power resource-constrained devices implementing specialized tasks, unlike general-purpose computers. Embedded systems find applications in various domains, from the Internet of Things (IoT) to general purpose Personal Computers (PC). Unfortunately, due to the resource constraints of embedded systems, developers often sacrifice security in favor of […]