no code implementations • 2 Sep 2022 • Ouya Wang, Jiabao Gao, Geoffrey Ye Li
Most of the existing works are based on data-driven deep learning, which requires a significant amount of training data for the communication model to adapt to new environments and results in huge computing resources for collecting data and retraining the model.
no code implementations • 21 Nov 2021 • Xinyu Wei, Biing-Hwang Fred Juang, Ouya Wang, Shenglong Zhou, Geoffrey Ye Li
In this paper, we propose a new learning method named Accretionary Learning (AL) to emulate human learning, in that the set of objects to be recognized may not be pre-specified.