Dynamic neural network is an emerging research topic in deep learning. Compared to static models which have fixed computational graphs and parameters at the inference stage, dynamic networks can ad…
Deep reinforcement learning (RL) agents are becoming increasingly proficient in a range of complex control tasks. However, the agent’s behavior is usually difficult to interpret due to the introd…
Data augmentation is widely known as a simple yet surprisingly effective technique for regularizing deep networks. Conventional data augmentation schemes, e.g., flipping, translation or rotation, a…
Deep reinforcement learning (RL) has recently led to many breakthroughs on a range of complex control tasks. However, the agent’s decision-making process is generally not transparent. The lack of…
We present a new technique to self-mitigate the RF power variations in microwave photonic phase shifters (MPPS) based on microring resonators by exploiting the root problem of varying optical inten…