H
Hanxiao Liu
Researcher at Google
Publications - 63
Citations - 9248
Hanxiao Liu is an academic researcher from Google. The author has contributed to research in topics: Computer science & Search algorithm. The author has an hindex of 26, co-authored 54 publications receiving 6109 citations. Previous affiliations of Hanxiao Liu include Carnegie Mellon University.
Papers
More filters
Proceedings Article
DARTS: Differentiable Architecture Search
TL;DR: The proposed algorithm excels in discovering high-performance convolutional architectures for image classification and recurrent architectures for language modeling, while being orders of magnitude faster than state-of-the-art non-differentiable techniques.
Posted Content
DARTS: Differentiable Architecture Search
TL;DR: In this article, the authors propose a differentiable architecture search algorithm based on the continuous relaxation of the architecture representation. But the architecture search is not a discrete and non-differentiable search space.
Proceedings ArticleDOI
Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networks
TL;DR: A novel deep learning framework, namely Long- and Short-term Time-series network (LSTNet), to address this open challenge of multivariate time series forecasting, using the Convolution Neural Network and the Recurrent Neural Network to extract short-term local dependency patterns among variables and to discover long-term patterns for time series trends.
Proceedings ArticleDOI
RACE: Large-scale ReAding Comprehension Dataset From Examinations
TL;DR: RACE as discussed by the authors is a dataset for benchmark evaluation of methods in reading comprehension task, collected from the English exams for middle and high school Chinese students in the age range between 12 to 18.
Proceedings Article
Hierarchical Representations for Efficient Architecture Search
TL;DR: In this article, a hierarchical genetic representation scheme was used to discover architectures for image classification, achieving a top-1 accuracy of 3.6% on CIFAR-10 and 20.3% on ImageNet.