Jung-Eun Kim

I am an assistant professor in Electrical Engineering & Computer Science (EECS) at Syracuse University. I am also a part of the Aging, Health, and Neuroscience (AHN) cluster. I am looking into AI/Machine learning through the lens of Systems. My research interests span Resource-/Time-dependent learning, AI/Machine learning for cyber-physical and embedded systems, Safety-/Time-critical systems, Embedded multicore systems. Prior to joining EECS Syracuse, I was an associate research scientist in Computer Science at Yale University. I received my PhD degree in Computer Science at the University of Illinois at Urbana-Champaign, and my BS and MS degrees from the department of Computer Science and Engineering at Seoul National University, Korea.

jkim150@syr.edu

Available Positions

I am looking for Phd/master/undergrad students who are highly motivated. Please reach out to me for potential research opportunities.

Research

Anytime Learning: resource-/time-dependent learning

Based on considerations of performance-resource trade-offs of learning applications especially in cyber-physical and embedded platforms operating in resource-constrained environment, the framework is designed with adaptive concreteness to produce a feasible answer quickly and to produce an improved answer by performing additional processing as time permits, instead of enforcing strict or predefined requirements for resource/quality. Moreover, the resource limit when the solution is required may not be known far in advance, so whenever possible, the system can be ready at all times to produce the highest-quality solution it has found so far. Hence, it provides “ballpark” early results, and gradually higher-quality later results.

.

AnytimeNet: Controlling Time-Quality Trade-Offs in Deep Neural Network Architectures

Deeper neural networks, in particular (which obtain near-state-of-the-art performance with complex structures and a large number of internal parameters), require a massive amount of CPU/GPU processing capacity to obtain solutions with rigorously refined quality. Over the ranges of interest, there is a trade-off between solution quality and the resource required to produce the solution. It is tackled by constructing a deep neural network in a modular and adaptive way – the framework breaks down this complexity into smaller building blocks, so as to facilitate implementation and maintenance. An instance is shown with simplified ResNet blocks – in early iterations, fewer number of blocks are used while in later iterations more blocks are used to provide gradually better results.

ABC: Abstraction Before Concreteness

Under the same umbrella and philosophy in mind with AnytimeNet above, for resource-scarce environment, neural network is designed for adaptive concreteness thru data hierarchy: learning abstract information earlyconcrete information later.  For example, as shown in the figure, recognizing a category that contains a “stop” sign (i.e., urgent signs) is more time-critical than one containing “speed limit” signs. This is because a stop sign requires early action in a timely manner. The intermediate results can be utilized to prepare for early decisions/actions as needed. To apply this framework to a classification task for example, the datasets are categorized in an abstraction hierarchy. Then the framework classifies intermediate labels from the most abstract level to the most concrete.

.

Selected Honors and Awards

  • CRA (Computing Research Association) Career Mentoring Workshop, 2022
  • NSF SaTC (Secure and Trustworthy Cyberspace): CORE: Small: Partition-Oblivious Real-Time Hierarchical Scheduling, Co-PI, National Science Foundation, 2020–2023
  • GPU Grant by NVIDIA Corporation, 2018
  • The MIT EECS Rising Stars, 2015
  • The Richard T. Cheng Endowed Fellowship, 2015 – 2016

.

Teaching

  • Intelligent cyber-physical system, Fall 2021
  • Data structures, Spring 2022

.

Conference / Journal Publication

Workshop Publications, Technical Reports, Dissertation

Presentations and Talks

  • Department of Computer Science at Yale University, lecture of Self-Driving Cars: Theory and Practice (CPSC 235/EENG 245), “Time-Dependent Machine Learning, to be incorporated in CPS,” Apr. 22, 2019.
  • Department of Computer Science at the University of Illinois at Urbana-Champaign, lecture of Embedded Systems (CS 431), “Decision-Centric Data Scheduling in Emerging Cyber-Physical Systems I & II,” Apr. 19 & 24, 2018.
  • Department of Computer Science at the University of Illinois at Urbana-Champaign, lecture of Modern Real-Time Systems (CS 598), “Decision-Centric Data Scheduling in Emerging Cyber-Physical Systems,” Nov. 8, 2017.
  • U.S. Army Research Laboratory, Adelphi, MD, “Decision-Centric Data Scheduling for Autonomous Cyber-Physical Systems,” Nov. 1, 2017.
  • The 20th ACM/IEEE Design, Automation, and Test in Europe (DATE 2017), “A Schedulability Test for Software Migration on Multicore Systems,” Mar. 30, 2017.
  • The 37th IEEE Real-Time Systems Symposium (RTSS 2016), “Sporadic Decision-centric Data Scheduling with Normally-off Sensors,” Dec. 1, 2016.
  • Rockwell Collins Inc., Community of Practice meeting, “Sporadic Decision-centric Data Scheduling with Normally-off Sensors,” Nov. 17, 2016.
  • The 22nd IEEE International Conference on Embedded and Real-Time Computing Systems and Applications, “On Maximizing Quality of Information for the Internet of Things: A Real-time Scheduling Perspective (Invited paper),” Aug. 19, 2016.
  • The MIT EECS Rising Stars 2015, “A New Real-Time Scheduling Paradigm for Safety-Critical Multicore Systems” Nov. 9, 2015.
  • The 21st IEEE Real-Time and Embedded Technology and Applications Symposium (RTAS 2015), “Budgeted Generalized Rate Monotonic Analysis for the Partitioned, Globally Scheduled Uniprocessor Model,” Apr. 16, 2015.
  • The 18th ACM/IEEE Design, Automation, and Test in Europe (DATE 2015), “Schedulability Bound for Integrated Modular Avionics Partitions,” Mar. 10, 2015.
  • Rockwell Collins Inc., Community of Practice meeting, “Integrated Modular Avionics (IMA) Partition Scheduling with Conflict-Free I/O for Multicore Avionics Systems,” Sep. 30, 2014.
  • The 38th IEEE Computer Software and Applications Conference, “Integrated Modular Avionics (IMA) Partition Scheduling with Conflict-Free I/O for Multicore Avionics Systems,” Jul. 23, 2014.
  • The 16th ACM/IEEE Design, Automation, and Test in Europe (DATE 2013), “Optimized Scheduling of Multi-IMA Partitions with Exclusive Region for Synchronized Real- Time Multi-Core System,” Mar. 20, 2013.
  • Rockwell Collins Inc., “Single Core Equivalent Configuration for Multicore Avionic Systems,” Aug. 15, 2012.
  • The 32th IEEE Real-Time Systems Symposium (RTSS 2011), “Optimizing Tunable WCET with Shared Resource Allocation and Arbitration in Hard Real-Time Multicore Systems,” Dec. 2, 2011.

Patent

  • Chang-Gun Lee, Jung-Eun Kim, and Junghee Han. Sensor Deployment System for 3-Coverage. KR 10-1032998, filed Dec. 30, 2008, and issued Apr. 27, 2011.