Select a calendar:
Filter May Events by Event Type:
Events for May 01, 2023
-
PhD Thesis Defense - Ehsan Qasemi
Mon, May 01, 2023 @ 10:30 AM - 12:30 PM
Thomas Lord Department of Computer Science
University Calendar
PhD Thesis Defense - Ehsan Qasemi
Title: Multi-Modal Preconditioned Inference of Commonsense Knowledge
Committee Members: Muhao Chen, Aiichiro Nakano, Daniel O Leary, Fred Morstatter, Luis Garcia
Abstract: Humans can seamlessly reason with circumstantial preconditions of commonsense knowledge. We understand that a glass is used for drinking water, unless the glass is broken or the water is toxic. Despite state-of-the-art (SOTA) models impressive performance in inferring commonsense knowledge, it is unclear whether they understand the circumstantial preconditions. In this dissertation, I initially propose a novel challenge of reasoning with preconditions attributed to commonsense knowledge, design three tasks based on the challenge in text-only setup, and show there is a significant gap between SOTA language models performance and humans on our tasks. I then use weak supervision in a combination of targeted fine-tuning strategies to improve the language models performance on the preconditioned inference task. Finally, I go beyond the text-only setup and investigate the problem of preconditioned inference in a multi-modal setup when the model is challenged to infer the preconditions from an image.
Audiences: Everyone Is Invited
Contact: Melissa Ochoa
Event Link: https://usc.zoom.us/j/98769460750
-
MoBI Seminar: Dr Daniel Toker
Mon, May 01, 2023 @ 11:00 AM - 12:00 PM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Dr Daniel Toker, Post-doctoral Fellow, Department of Psychology | Department of Neurology, University of California, Los Angeles
Talk Title: Criticality supports thalamocortical information processing during conscious states
Series: MoBI Seminar Series
Abstract: Mounting evidence suggests that during conscious states, neural electrodynamics are poised near a critical point or phase transition, and that this near-critical behavior supports the vast flow of information through thalamocortical networks during waking states. We identify a mathematically specific critical point near which waking neural electrodynamics operate, which is known as the edge-of-chaos critical point, or the boundary between stability and chaos. Our evidence suggests that both the information-richness of cortical activity and the transfer of information between the cortex and thalamus is disrupted during diverse states of unconsciousness because of a transition of low-frequency thalamocortical electric oscillations away from this critical point. Conversely, we show that psychedelics may increase the information-richness of cortical activity and enhance communication between the thalamus and cortex by tuning low-frequency thalamocortical electrodynamics closer to this critical point.
Biography: Daniel Toker, PhD is a post-doctoral fellow in UCLA's Departments of Psychology and Neurology. He uses human and animal electrophysiology, mathematical modeling, and human brain organoids to study mechanisms underlying the loss and recovery of consciousness from anesthesia, generalized seizures, and coma.
Host: Dr Richard Leahy, leahy@sipi.usc.edu | Dr Karim Jerbi, karim.jerbi.udem@gmail.com
Webcast: https://usc.zoom.us/j/99475118848?pwd=ekJELzlxR1FPamwxRFp4cEgrNktRZz09More Information: MoBI Seminar Flyer - 05.01.2023 Daniel Toker.pdf
Location: Hughes Aircraft Electrical Engineering Center (EEB) - EEB 132
WebCast Link: https://usc.zoom.us/j/99475118848?pwd=ekJELzlxR1FPamwxRFp4cEgrNktRZz09
Audiences: Everyone Is Invited
Contact: Miki Arlen
-
Atoms Bits & Cells Finals
Mon, May 01, 2023 @ 02:00 PM - 04:00 PM
Viterbi Technology Innovation and Entrepreneurship
Receptions & Special Events
Atoms Bit & Cells is an undergrad competition and program to innovation and develop solutions in three areas:
Atoms â“ engineering hardware products
Bits â“ digital projects, such as mobile and web apps, including AI, ML applications
Cells â“ biomedical or bioengineering projects
Come and hear from the ABC teams as they present their technology and business. While the compete for a 1k prize towards their business.Location: Hughes Aircraft Electrical Engineering Center (EEB) - 132
Audiences: Everyone Is Invited
Contact: Viterbi TIE
-
PhD Dissertation Defense - Wenxuan Zhou
Mon, May 01, 2023 @ 04:00 PM - 05:00 PM
Thomas Lord Department of Computer Science
University Calendar
PhD Dissertation Defense - Wenxuan Zhou
Title: Robust and Generalizable Knowledge Acquisition from Text
Committee members: Muhao Chen (chair), Laurent Itti, Tianshun Sun, Robin Jia, Jonathan May
Abstract: With large amounts of digital text generated every day, it is important to acquire structured knowledge automatically from the text. In my thesis, I will present my work during my Ph.D. from two perspectives: (1) Improving the robustness of knowledge acquisition, especially against bias from training corpus; and (2) building data-efficient knowledge acquisition models in low-resource scenarios, which is important for tasks in high-stake domains. After these, I will discuss challenges and future directions for both (1) and (2).Audiences: Everyone Is Invited
Contact: Melissa Ochoa
Event Link: https://usc.zoom.us/j/6915039300