Keynote I: Deep learning: Some open research directions

     Deep learning has been successfully applied to a very broad variety of fields including image recognition, text generation, autonomous driving, etc. Despite this success, deep learning suffers from a number of problems that constitute active and promising research directions. This talk is aimed to address some of those issues, including the lack of large amounts of high-quality labeled data and how this conducted researchers to investigate or adapt weakly supervised learning approaches like semi supervised learning and active learning. This talk will also skim over transfer learning, and why it can help deal with the limitation in processing capacity and/or the lack of data. In particular, the scalability issue will be considered, along with why distributed deep learning and deep learning on the cloud are promising solutions. Other promising research directions that will be discussed include the choice of the right optimization method, explanability issue, as well as some other learning paradigms such as reinforcement learning and continual learning. Recent works in some of those directions will be illustrated, along with some real-life examples of applications.

  Keynote II: Blockchain and Artificial Intelligence for Cyber Security in the Era of IoT and IIoT applications: Research challenges

     When an adversary attempts to penetrate the network, it uses several different approaches such as DDoS attacks, scanning attacks, false data injection attacks, to disrupt the functioning of the IoT-based devices. To protect Industry 5.0 from destruction, change, unauthorized access, or attack, Security researchers propose the use of an intrusion detection system (IDS) combined the blockchain technology. The IDS system is a mechanism monitoring the network traffic, which is used to detect suspicious or abnormal activities and then enables preventive measures on the intrusion risks. The blockchain technology is used to detect fraudulent transactions. In this talk, we will first discuss blockchain technology as well as artificial intelligence for cyber security in IoT and IIoT applications. Next, we will move to survey some solutions developed by our research group, intended to provide security to IoT and IIoT applications. Finally, we will conclude by highlighting topic-related research directions.

  Keynote III: From the IoT and IIoT to the Artificial Intelligence of Things : Opportunities and Challenges

     The Internet of Things (IoT) bridges the gap between the cyber and physical worlds by interconnecting computationally, memory, and energy-constrained sensors and actuators to the Internet and opens unprecedented opportunities. This has become true thanks to recent advances in telecommunications, micro-electromechanical systems, and embedded software engineering, along with tremendous research and standardization efforts. In this talk, we will discuss the current state of the art in the fields of IoT, IIoT, and AIoT as well as their future trends and expectations. We will first introduce the offered opportunities, then move on to discuss the challenges and the current research efforts to address them in both academia and industry. The talk ends by presenting some practical AIoT applications and prototypes designed at the EMP and lays down ways for future research and opportunities.