Select a calendar:
Filter February Events by Event Type:
Events for February 28, 2023
-
CS Colloquium: Yang Liu (UC Santa Cruz) - Reliable Machine Learning: From Data to Deployment
Tue, Feb 28, 2023 @ 11:00 AM - 12:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Yang Liu, UC Santa Cruz
Talk Title: Reliable Machine Learning: From Data to Deployment
Series: CS Colloquium
Abstract: Developing reliable machine learning systems presents challenges in handling biased input data and the consequences of deployment. For instance, a machine learning model for question answering (e.g., ChatGPT) can encode mistakes and biases that persist in the database; an unaware machine learning-powered decision-maker (e.g., for loan approval) can automatically deny people the chance of recourse, resulting in a decline of trust between human and machines; deploying a sequence of myopically optimized models may create an unfair "echo chamber" for users. The list goes on. This talk presents three challenges to building a reliable machine learning system: (1) developing fair and robust algorithms with biased training data, (2) auditing the dynamic interactions between users and machine learning models, and (3) maximizing the long-term welfare of machine learning ecosystems with efficient interventions. We will discuss our group's efforts in addressing these challenges.
This lecture satisfies requirements for CSCI 591: Research Colloquium
Biography: Yang Liu is an Assistant Professor of Computer Science and Engineering at UC Santa Cruz (2019 - present). He also leads the machine learning fairness team at ByteDance AI Lab. He was previously a postdoctoral fellow at Harvard University (2016 - 2018). In 2015, he received his Ph.D. degree from the Department of EECS at the University of Michigan, Ann Arbor. His research focuses on developing fair and robust machine learning algorithms to tackle the challenges of biased and shifting data. He is a recipient of the NSF CAREER Award. He has been selected to participate in several high-profile projects, including NSF-Amazon Fairness in AI, DARPA SCORE, and IARPA HFC. His research has observed deployments with FICO and Amazon. His recent work has been recognized with four best paper awards at relevant workshops.
Host: Vatsal Sharan
Location: Olin Hall of Engineering (OHE) - 132
Audiences: Everyone Is Invited
Contact: Assistant to CS chair
This event is open to all eligible individuals. USC Viterbi operates all of its activities consistent with the University's Notice of Non-Discrimination. Eligibility is not determined based on race, sex, ethnicity, sexual orientation, or any other prohibited factor.
-
PhD Candidate: Shichen Liu
Tue, Feb 28, 2023 @ 03:00 PM - 04:00 PM
Thomas Lord Department of Computer Science
University Calendar
Title: Learning to Optimize the Geometry and Appearance from Images.
Abstract:
The ability to infer geometry and appearance from images impacts various applications such as AR/VR, autonomous driving, and more. Compared to traditional methods, deep convolutional neural networks have proven to be more robust and accurate. However, the practical use of deep learning in these applications still faces three major challenges: (1) the acquisition of 3D training data; (2) the development of a fast, robust, and accurate 3D vision framework; (3) the integration of complex 3D representations into the neural network.
To address these challenges, my research focuses on optimization techniques in the context of deep learning. Specifically, when paired 2D and 3D data is not available, we propose a differentiable rendering framework that allows neural networks to learn 3D shapes directly from 2D images. On the other hand, when full supervision is available, we develop a framework that trains a neural network to optimize the target representation and demonstrate the performance on the vanishing point detection task. Finally, we explore the face avatar creation task and propose dense visual-semantic correlation on top of a semantically-aligned UV space to effectively integrate complex 3D representations into the neural optimization framework. Our neural optimization techniques help to develop practical 3D computer vision systems.
Committee members are Randall Hill, Andrew Nealen, Aiichiro Nakano, Stefanos Nikolaidis, and Yajie Zhao.
Location: https://usc.zoom.us/j/3154287574.
Audiences: Everyone Is Invited
Contact: Asiroh Cham
Event Link: https://usc.zoom.us/j/3154287574
This event is open to all eligible individuals. USC Viterbi operates all of its activities consistent with the University's Notice of Non-Discrimination. Eligibility is not determined based on race, sex, ethnicity, sexual orientation, or any other prohibited factor.
