Select a calendar:
Filter May Events by Event Type:
Events for the 2nd week of May
-
ECE Seminar: Robust Classification under Sparse Adversarial Attacks
Mon, May 08, 2023 @ 10:00 AM - 11:00 AM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Dr. Payam Delgosha, Research Assistant Professor, Computer Science Department, University of Illinois at Urbana Champaign
Talk Title: Robust Classification under Sparse Adversarial Attacks
Abstract: It is well-known that machine learning models are vulnerable to small but cleverly-designed adversarial perturbations that can cause misclassification. While there has been major progress in designing attacks and defenses for various adversarial settings, many fundamental and theoretical problems are yet to be resolved. In this talk, we consider classification in the presence of L0-bounded adversarial perturbations, a.k.a. sparse attacks. This setting is significantly different from other Lp-adversarial settings, with p >= 1, as the L0-ball is non-convex and highly non-smooth. In this talk, we discuss the fundamental limits of robustness in the presence of sparse attacks. In order to find an upper bound on the robust error, we introduce novel classification methods that are based on truncation. Furthermore, in order to find a lower bound on the robust error, we design a specific adversarial strategy which tries to remove the information about the true label given the adversary's budget. We discuss scenarios where the bounds match asymptotically. Motivated by the theoretical success of the proposed algorithm, we discuss how to incorporate truncation as a new component into a neural network architecture, and verify the robustness of the proposed architecture against sparse attacks through several experiments. Finally, we investigate the generalization properties and sample complexity of adversarial training in this setting.
Biography: Payam Delgosha received his B.Sc. in Electrical Engineering and Pure Mathematics in 2012, and his M.Sc. in Electrical Engineering in 2014, both from Sharif University of Technology, Tehran, Iran. He received his Ph.D. in Electrical Engineering and Computer Sciences from the University of California at Berkeley in 2020. He joined the computer science department at the University of Illinois at Urbana Champaign as a research assistant professor in 2020. He received the 2020 IEEE Jack Keil Wolf ISIT best student paper award.
Host: Dr. Richard M. Leahy, leahy@sipi.usc.edu
Webcast: https://usc.zoom.us/j/97124212376?pwd=NTd0QzRzSXk3OGlzL0dIdFdXMmZYZz09More Information: ECE Seminar-Delgosha-050823.pdf
WebCast Link: https://usc.zoom.us/j/97124212376?pwd=NTd0QzRzSXk3OGlzL0dIdFdXMmZYZz09
Audiences: Everyone Is Invited
Contact: Mayumi Thrasher
-
MoBI Seminar: Dr Bradley Voytek
Mon, May 08, 2023 @ 11:00 AM - 12:00 PM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Dr Bradley Voytek, Department of Cognitive Science, HalıcıoÄlu Data Science Institute, UC San Diego
Talk Title: The physiology and function of aperiodic neural activity
Series: MoBI Seminar Series
Abstract: Perception, action, and cognition depend upon coordinated neural activity. This coordination operates within noisy, distributed neural networks, which themselves change with development, aging, and disease. Extensive field potential and EEG research shows that neural oscillations interact with neuronal spiking. This interaction has been proposed to be a mechanism for implementing dynamic coordination between brain regions, placing oscillations at the forefront of neuroscience research. Our work challenges our conception of what an oscillation even is. Beginning from basic theory and modeling, we show that traditional analyses conflate non-oscillatory, aperiodic activity with oscillations. To do this, we leverage neural modeling and a breadth of empirical data-”spanning human iPSC-derived cortical organoids, animal electrophysiology, invasive human EEG, and large-scale data mining. We show that, while not all things that appear oscillatory are so, the physiological information we can extract from the local field potential and EEG may nevertheless be far richer than previously thought, including nonsinusoidality of oscillation waveform shape and the aperiodic signal.
Biography: Bradley Voytek is a Professor in the Department of Cognitive Science, the HalıcıoÄlu Data Science Institute, and the Neurosciences Graduate Program at UC San Diego. He's an Alfred P. Sloan Neuroscience Research Fellow and a Kavli Fellow of the National Academies of Sciences, as well as a founding faculty member of the UC San Diego HalıcıoÄlu Data Science Institute and the Undergraduate Data Science program. After his PhD at UC Berkeley, he joined Uber as their first data scientist-”when it was a 10-person startup-”where he helped build their data science strategy and team. His research lab combines large-scale data science and machine learning to study how brain regions communicate with one another, and how that communication changes with aging and disease. He is an advocate for promoting science to the public and speaks extensively with students at all grade levels about the joys of scientific research and discovery. In addition to his academic publications, his outreach work has appeared in outlets ranging from Scientific American and NPR to the San Diego Comic-Con. He is currently writing a book with neuroscientist Ashley Juavinett regarding the powerful future of data science in neuroscience discovery, though his most important contribution to science is his book with fellow neuroscientist Tim Verstynen, "Do Zombies Dream of Undead Sheep?", by Princeton University Press.
Host: Dr Richard Leahy, leahy@sipi.usc.edu | Dr Karim Jerbi, karim.jerbi.udem@gmail.com
Webcast: https://usc.zoom.us/j/97647013783?pwd=d1h2N3hxYUpJVU9CWlduYTZzMWNGQT09More Information: MoBI Seminar Flyer - 05.08.2023 Bradley Voytek.pdf
Location: Hughes Aircraft Electrical Engineering Center (EEB) - EEB 132
WebCast Link: https://usc.zoom.us/j/97647013783?pwd=d1h2N3hxYUpJVU9CWlduYTZzMWNGQT09
Audiences: Everyone Is Invited
Contact: Miki Arlen
-
PhD Thesis Proposal - Mehrnoosh Mirtaheri
Mon, May 08, 2023 @ 02:00 PM - 03:30 PM
Thomas Lord Department of Computer Science
University Calendar
PhD Thesis Proposal - Mehrnoosh Mirtaheri
Committee members: Aram Galstyan, Mohammad Rostami, Fred Morstatter, Cyrus Shahabi, Antonio Ortega
Title: Scalable Graph-Based Models for Temporal Knowledge Graphs: Learning, Applications
Abstract: Temporal knowledge graphs (TKGs) have emerged as a powerful tool for modeling relationships between entities in large raw text datasets. By capturing and representing these relationships in a structured, interpretable format, TKGs enable the extraction of valuable insights from vast amounts of unstructured information. Knowledge graphs allow for the identification of patterns and trends over time, enhancing our understanding of evolving connections and interactions between various entities. Moreover, they facilitate complex reasoning tasks, question answering, and data driven decision making by offering a more comprehensive view of the relationships found within the text.
This thesis focuses on developing various models to address different challenges associated with TKG completion, such as data scarcity, scalability, and continuously evolving data. By tackling these challenges, the proposed models aim to enhance the capabilities of TKGs for analyzing and processing complex relationships within large scale text data. As a result, they enable more accurate and effective knowledge extraction and representation. The advancements presented in this thesis can greatly benefit a wide range of applications that rely on understanding the underlying structure of relationships in massive raw text datasets.
Audiences: Everyone Is Invited
Contact: Melissa Ochoa
Event Link: https://usc.zoom.us/j/99893841028?pwd=RlhVd29VcTltdnFCRW54dHc3ZjhrZz09
-
PhD Thesis Proposal - Yufeng Yin
Mon, May 08, 2023 @ 02:00 PM - 04:00 PM
Thomas Lord Department of Computer Science
University Calendar
PhD Thesis Proposal - Yufeng Yin
Committee Members: Mohammad Soleymani (chair), Jonathan Gratch, Mayank Kejriwal, Lynn Miller, Maja Mataric, and Xuezhe Ma
Title: Towards Generalizable Facial Expression and Emotion Recognition
Abstract: Facial expression and emotion recognition are critical components of human behavior understanding. However, the performance of automatic recognition methods degrades when evaluated across datasets or subjects, due to variations in humans and environmental factors. The manual coding required by supervised methods also presents significant practical limitations since they are not feasible when working with new datasets or individuals.
In this thesis proposal, we investigate how to improve the generalization ability of the perception model through representation learning and synthetic data generation with minimal human efforts. (i) We explore unsupervised domain adaptation (UDA) approaches to obtain domain invariant and discriminative features without any target labels. The experiments show that UDA can effectively reduce the domain gap between datasets or subjects and improve model cross corpus performance for emotion recognition. (ii) We explore approaches for synthetic data generation to address the problems of the scarcity of labeled data and the diversity of subjects. Our results indicate that synthetic data can not only improve action unit (AU) detection performance but also fairness across genders, demonstrating its potential to solve AU detection in the wild. We will also discuss our future work involving unsupervised personalization on unseen speakers for emotion recognition through feature representation learning and label distribution calibration. Our proposed methods enhance model recognition accuracy and generalization ability to unseen subjects and datasets, paving the way for more effective human behavior analysis in a variety of applications.
Audiences: Everyone Is Invited
Contact: Melissa Ochoa
Event Link: https://usc.zoom.us/j/94638614965?pwd=c0ozL09VVjVBNmNwRmQ4NTAybWwzdz09
-
PhD Defense - Isabel Rayas
Mon, May 08, 2023 @ 02:00 PM - 04:00 PM
Thomas Lord Department of Computer Science
University Calendar
PhD Candidate Defense: Isabel Rayas
In-person: RTH 306
Zoom: https://usc.zoom.us/j/95235693966?pwd=cE92UC8zejROMi8yYytyT3F5YnY1UT09
Committee:
Gaurav Sukhatme (Chair), David Caron, Stefanos Nikolaidis
Title: Advancing Robot Autonomy for Long-Horizon Tasks
Abstract:
Autonomous robots have real-world applications in diverse fields, such as mobile manipulation and environmental exploration, and many such tasks benefit from a hands-off approach in terms of human user involvement over a long task horizon. However, the level of autonomy achievable by a deployment is limited in part by the problem definition or task specification required by the system. Task specifications often require technical, low-level information that is unintuitive to describe and may result in generic solutions, burdening the user technically both before and after task completion. In this thesis, we aim to advance task specification abstraction toward the goal of increasing robot autonomy in real-world scenarios. We do so by tackling problems that address several different angles of this goal. First, we develop a way for the automatic discovery of optimal transition points between subtasks in the context of constrained mobile manipulation, removing the need for the human to hand-specify these in the task specification. We further propose a way to automatically describe constraints on robot motion by using demonstrated data as opposed to manually-defined constraints. Then, within the context of environmental exploration, we propose a flexible task specification framework, requiring just a set of quantiles of interest from the user that allows the robot to directly suggest locations in the environment for the user to study. We next systematically study the effect of including a robot team in the task specification and show that multirobot teams have the ability to improve performance under certain specification conditions, including enabling inter-robot communication. Finally, we propose methods for a communication protocol that autonomously selects useful but limited information to share with the other robots.
Location: Ronald Tutor Hall of Engineering (RTH) - 306
Audiences: Everyone Is Invited
Contact: Asiroh Cham
-
PhD Defense - Michiel De Jong
Mon, May 08, 2023 @ 03:00 PM - 05:00 PM
Thomas Lord Department of Computer Science
University Calendar
Title: EXPANDING THE QUALITY-COMPUTE FRONTIER FOR RETRIEVAL-AUGMENTED LANGUAGE MODELS
Abstract: Retrieval-augmented language models set the state-of-the-art on a broad spectrum of knowledge-intensive tasks, outperforming orders of magnitude larger models. However, such models can also be expensive for training and inference. Model performance and computational cost represent two sides of the coin: we can generally improve performance through scale at the expense of an increased computational burden. Therefore, we are really interested in pushing out the quality-compute frontier, improving performance at any given level of computational resources.
In this dissertation, I analyze the factors that determine the computational burden of retrieval-augmented language models and propose strategies to extract a better performance-compute trade-off. The dissertation consists of three sections. The first section contains a detailed analysis of components of retrieval-augmented models and introduces methods to improve generation efficiency. The second section explores the use of dense memory to reduce the cost of encoding retrievals. Finally, the third section proposes a hybrid between dense memory and text retrieval, combining lessons from previous chapters.
Names of the Dissertation defense committee members:
Chair: Leana Golubchik
Members:
Fei Sha
Dani Yogatama
Jacob Bien
Venue: Zoom, https://usc.zoom.us/my/lgzoomeeting
Location: https://usc.zoom.us/my/lgzoomeeting
Audiences: Everyone Is Invited
Contact: Asiroh Cham
-
Kuldeep Meel (National University of Singapore) - Functional Synthesis: An Ideal Meeting Ground for Formal Methods and Machine Learning
Tue, May 09, 2023 @ 11:00 AM - 12:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Kuldeep Meel, National University of Singapore
Talk Title: Functional Synthesis: An Ideal Meeting Ground for Formal Methods and Machine Learning
Abstract: Don't we all dream of the perfect assistant whom we can just tell what to do and the assistant can figure out how to accomplish the tasks? Formally, given a specification F(X,Y) over the set of input variables X and output variables Y, we want the assistant, aka functional synthesis engine, to design a function G such that F(X,G(X)) is true. Functional synthesis has been studied for over 150 years, dating back Boole in 1850's and yet scalability remains a core challenge. Motivated by progress in machine learning, we design a new algorithmic framework Manthan, which views functional synthesis as a classification problem, relying on advances in constrained sampling for data generation, and advances in automated reasoning for a novel proof-guided refinement and provable verification. The significant performance improvements call for interesting future work at the intersection of machine learning, constrained sampling, and automated reasoning.
Biography: Kuldeep Meel holds the NUS Presidential Young Professorship in the School of Computing at the National University of Singapore (NUS). His research interests lie at the intersection of Formal Methods and Artificial Intelligence. He is a recipient of the 2022 ACP Early Career Researcher Award, the 2019 NRF Fellowship for AI and was named AI's 10 to Watch by IEEE Intelligent Systems in 2020. His research program's recent recognitions include the CACM Research Highlight Award, 2022 ACM SIGMOD Research Highlight, IJCAI-22 Early Career Spotlight, best paper award nominations at ICCAD-21 and DATE-23.
Host: Mukund Raghothaman
Location: Olin Hall of Engineering (OHE) - 132
Audiences: Everyone Is Invited
-
PhD Dissertation Defense - Zimo Li
Tue, May 09, 2023 @ 02:00 PM - 04:00 PM
Thomas Lord Department of Computer Science
University Calendar
PhD Dissertation Defense - Zimo Li
Committee Members: Andrew Nealen, Laurent Itti, Stefanos Nikolaidis, Mike Zyda
Title: Human Appearance and Performance Synthesis Using Deep Learnin
Abstract: Synthesis of human performances is a highly sought after technology in the entertainment industry. In this dissertation, we will go over several new deep learning solutions which tackle the problems of human facial and body performance synthesis.
Facial performance synthesis is a complex multistep graphics problem. First, the target performance to be modified must be tracked and captured accurately. Then, based on the desired modification (whether to change the identity, facial expressions, or both), a modified source performance must be synthesized or captured from a different actor. Finally, the original facial performance must be removed and replaced with the synthesized one. This multistep process poses many unique challenges. Using conventional CG tracking and retargeting of expressions from the source to target using a 3D mesh and static texture will give an undesired rubbery skin effect. Furthermore, inaccuracies in the expression tracking of the source performance using a blendshape model will result in the uncanny valley effect in the output performance. It is often necessary to use costly capture methods, such as a Light Stage, to obtain highly accurate 3D captures and dynamic textures of a source performance in order to avoid these pitfalls. Even then, final modified performances are often uncanny.
When dealing with human body to motion synthesis, creating new motions often requires manual artist animations, tracking new motions on an actor, or stitching together subsequences of previous animations. These methods are limited by cost, or are not able to generate appreciably novel motions.
Over the last several years, the advancement of AI based generation techniques have let us address many of these issues. In this thesis, we will go over several novel techniques which reduce the cost (time, money, ease-of-access), and improve the quality of facial reenactment, as well as body motion synthesis, pipelines. The applications of these techniques allow us to tackle new problem settings in an efficient way.
Audiences: Everyone Is Invited
Contact: Melissa Ochoa
Event Link: https://us05web.zoom.us/j/86385849747?pwd=V2lwR2FXekI5WVpNMGU0bWF5clJIQT09
-
Innovation For Defense Applications Showcase
Tue, May 09, 2023 @ 04:30 PM - 06:30 PM
Viterbi Technology Innovation and Entrepreneurship
University Calendar
You are invited to join us for the Innovation For Defense Applications team presentations showcase. This semester we have teams that have worked on various problems sets for their Department of Defense sponsors.
The event will be held on the USC campus at the Ronald Tutor Hall (RTH) in room 526. Doors will open at 4:30 pm and will include light refreshments at the event.
If you can not attend in person, we will also provide a ZOOM link for a virtual option.
RSVP
Location: Ronald Tutor Hall of Engineering (RTH) - 526
Audiences: Everyone Is Invited
Contact: Johannah Murray
Event Link: https://forms.gle/EZP7rh2y4uPHMcne7