Skip to main content

Semantics-Native and Knowledge-Driven 6G Semantic Communication

Save to calendar

Aug 22

Date and time: 22 August 2022, 10:00 – 11:00 CEST (UTC +2)
Speaker: Jihong Park, Deakin University, Australia
Title: Semantics-Native and Knowledge-Driven 6G Semantic Communication

Where: Darlington, floor 4, Electrum, Kista, or attend online:
Zoom: https://kth-se.zoom.us/j/69560887455
Meeting ID: 695 6088 7455
Password: 755440

Picture of Jihong ParkAbstract: Often, humans can immediately respond to unseen events without instantaneously communicating with others. This is thanks to the ability to reason about future events, others’ minds, and their possible reactions to the events based on the background knowledge accumulated from experiences and communication in the past. Suppose 6G is genuinely about human-machine interaction and communication for intelligent machines. In that case, we can learn from human cognition and imbue such a reasoning capability into machines by leveraging the recent advances in artificial intelligence (AI) and communicating local knowledge across machines.

This boils down to developing a human-level semantic communication framework wherein AI-native machines understand the meanings of messages within contexts and communicate the intended meanings to maximize the effectiveness of their intended listener’s tasks. As the first step towards achieving this ambitious goal, in this talk, I will trace back to the fundamentals of human cognition and AI and introduce the ways to deal with semantics and knowledge in various disciplines, including linguistics, semiotics, logic, and category theory. Based on this, I will introduce several promising ways to enable AI-native and human-level semantic communication with selected examples using multi-agent reinforcement learning and probabilistic logic programming.

Bio:  Jihong Park is a Lecturer at the School of IT, Deakin University, Australia. He received his B.S. and PhD degrees from Yonsei University, Seoul, Korea, in 2009 and 2016, respectively. He was a Post-Doctoral Researcher with Aalborg University, Denmark, from 2016 to 2017; the University of Oulu, Finland, from 2018 to 2019. His recent research focus includes communication-efficient distributed machine learning, distributed control, distributed ledger technology, and their applications beyond 5G/6G communication systems.

He served as a Conference/Workshop Program Committee Member for IEEE GLOBECOM, ICC, and INFOCOM, as well as NeurIPS, ICML, and IJCAI. He received the IEEE GLOBECOM Student Travel Grant in 2014, the IEEE Seoul Section Student Paper Contest Bronze Prize in 2014, the 6th IDIS-ETNEWS (The Electronic Times) Paper Contest Award sponsored by the Ministry of Science, ICT, and Future Planning of Korea, and FL-IJCAI Best Student Paper Award in 2022. He is an Associate Editor of Frontiers in Data Science for Communications and Signal Processing for Communications, a Senior Member of IEEE and ACM.
  
Link to speaker’s webpage: https://sites.google.com/view/jihong-park 
Link to LinkedIn account: https://www.linkedin.com/in/jhparkjames/