DAIS Seminars

Spring 2024 Reading List

The written exam of the DAIS Qual Exam in Spring 2024 will be held on Monday, Feb. 26, 2024, at 1pm-5pm in room 0220 Siebel Center, which is in the basement of Siebel Center (floor map: https://facilityaccessmaps.fs.illinois.edu/archibus/schema/ab-products/essential/workplace/?blId=0563&flId=00).  This reading list consists of  multiple topic sections, each containing 2-3 papers.  The questions in the written exam […]

Fall 2023

The written exam of the DAIS Qual Exam in Fall 2023 will be held on Friday, Oct. 6, 2023, at 1pm-5pm in room 2124 Siebel Center.  This reading list consists of  multiple topic sections, each containing 2-3 papers.  The questions in the written exam will be based on the papers listed here, with 1-2 questions […]

Spring 2023

The written exam of the DAIS Qual Exam in Spring 2023 will be held on Monday, Feb. 20, 2023, at 1pm-5pm in room 2407 Siebel Center.  This reading list consists of  multiple topic sections, each containing 2-3 papers.  The questions in the written exam will be based on the papers listed here, with 1-2 questions […]

Fall 2022

The written exam of the DAIS Qual Exam in Fall 2022 will be held on Monday, Oct. 3, 2022, at 1pm-5pm in Siebel Center room 3401. This reading list consists of  multiple topic sections, each containing 2-3 papers.  The questions in the written exam will be based on the papers listed here, with 1-2 questions […]

Spring 2022

The DAIS Qual Exam in Spring 2022 has been scheduled to be at 1-5pm on Monday, Feb. 28, 2022.  This reading list consists of  multiple topic sections, each containing 2-3 papers.  The questions in the written exam will be based on the papers listed here, with 1-2 questions related to each section. That is, if […]

Fall 2021

The DAIS Qual Exam in Fall 2021 has been scheduled to be at 1-5pm on Monday, Oct. 4, 2021.  This reading list consists of  multiple topic sections, each containing 2-3 papers.  The questions in the written exam will be based on the papers listed here, with 1-2 questions related to each section. That is, if […]

Towards Theoretical Understanding of Overparametrization in Deep Learning

Guest Speaker: Jason Lee, Assistant Professor, University of Southern California Date/Time: Thursday, October 4, 2018, 2:00 pm Location: 3403 Siebel Sponsored by the Department of Computer Science and DAIS   Abstract: We provide new theoretical insights on why over-parametrization is effective in learning neural networks. For a k hidden node shallow network with quadratic activation […]