Adaptive AI
Adaptive AI focuses on creating artificial intelligence systems that can continuously learn and improve their performance in dynamic environments, adapting to new data and changing conditions without human intervention. Current research emphasizes reinforcement learning, particularly deep Q-networks, and active inference frameworks, along with the use of graphical neural networks for time-series data and the integration of brain-computer interfaces. This field is significant for enhancing the robustness and efficiency of AI across diverse applications, from healthcare and robotics to language processing and communication systems, ultimately leading to more reliable and user-friendly AI tools.
Papers
Graph-enabled Reinforcement Learning for Time Series Forecasting with Adaptive Intelligence
Thanveer Shaik, Xiaohui Tao, Haoran Xie, Lin Li, Jianming Yong, Yuefeng Li
Self-Sustaining Multiple Access with Continual Deep Reinforcement Learning for Dynamic Metaverse Applications
Hamidreza Mazandarani, Masoud Shokrnezhad, Tarik Taleb, Richard Li