Wireless Artificial Intelligence - ConNected Learning with CNL, Sogang University, Led by Prof. Jaewoo So

Communications and Network Lab (CNL), Sogang University Wireless AI and Wireless Connectivity

IEEE ComSoc, March, 2019 Best Readings in Machine Learning in Communications

IEEE Communications Magazine, March, 2019 Artificial Intelligence in Wireless Communications

Wireless AI - AI Empowered 5G/6G, IoT, and Smart Car:

AI for wireless communications AI for resource allocation and transmit control, e.g., channel allocation, power and rate control AI for physical layer issues, e.g., channel estimation, interference alignment, AI for traffic engineering, scheduling, network slicing and virtualization AI for emerging networks and simulations AI in emerging networks, e.g., wireless powered networks, UAVs, URLLC, V2X, etc. AI for network coexistence, e.g., HetNet, cognitive radio, device-to-device networks Testbed, experiments, and simulations of AI in communications and networking

AI in wireless communications: Artificial intelligence (AI), which learns from the perceived environment and can exploit the increasingly massive datasets available from wireless systems, can be used to solve complex and previously intractable problems. Many problems in wireless communication systems, such as decision making, resource optimization, and network management, can be cast in a form that is suitable to be solved by AI techniques. Hence, AI technologies have been applied to improve the performance of future wireless communication systems. We focus on the design of AI empowered PHY, MAC, and network layers for 6G.
Machine learning (ML) for wireless resource allocation and interference mitigation: Resource management problems in systems and networking often manifest as difficult online decision making tasks where appropriate solutions depend on understanding the workload and environment. We apply recent AI technologies to wireless networks.
Deep reinforcement learning (DRL) for wireless and mobile networking: The integration of DRL into future wireless networks will revolutionize the conventional model-based network optimization to model-free approaches and meet various application demands. By interacting with the environment, DRL provides an autonomous decision-making mechanism for the network entities to solve non-convex, complex model-free problems, e.g., spectrum access, handover, scheduling, caching, data offloading, and resource allocation.

AI empowered 6G
RNN-based Solution for 5G Massive MIMO	Reconfigurable Deep Learning Framework for AI-aided 5G BS systems
CNL's Machine Learning for Wireless Networks	CNL's Machine Learning Simulator (developing '19)

#