Y
Yihan Jiang
Researcher at University of Washington
Publications - 29
Citations - 1043
Yihan Jiang is an academic researcher from University of Washington. The author has contributed to research in topics: Communication channel & Deep learning. The author has an hindex of 12, co-authored 21 publications receiving 666 citations.
Papers
More filters
Posted Content
Improving Federated Learning Personalization via Model Agnostic Meta Learning.
TL;DR: This work points out that the setting of Model Agnostic Meta Learning (MAML), where one optimizes for a fast, gradient-based, few-shot adaptation to a heterogeneous distribution of tasks, has a number of similarities with the objective of personalization for FL.
Proceedings Article
Communication algorithms via deep learning
TL;DR: It is shown that creatively designed and trained RNN architectures can decode well known sequential codes such as the convolutional and turbo codes with close to optimal performance on the additive white Gaussian noise (AWGN) channel.
Proceedings Article
Deepcode: Feedback Codes via Deep Learning
TL;DR: In this article, the Gaussian noise channel with feedback is considered, and the first family of codes obtained via deep learning is presented, which significantly beats state-of-the-art codes designed over several decades of research.
Journal ArticleDOI
Deepcode: Feedback Codes via Deep Learning
TL;DR: In this article, the Gaussian noise channel with feedback was considered, and the first family of codes obtained via deep learning was presented, which significantly outperformed state-of-the-art codes designed over several decades of research.
Posted Content
Communication Algorithms via Deep Learning.
TL;DR: In this article, the authors study a family of sequential codes parameterized by recurrent neural network (RNN) architectures and show that creatively designed and trained RNN architectures can decode well known sequential codes such as the convolutional and turbo codes with close to optimal performance on the additive white Gaussian noise (AWGN) channel.