Search Results for author: Hua Jiang

Found 10 papers, 2 papers with code

Hybrid Learning with New Value Function for the Maximum Common Subgraph Problem

no code implementations18 Aug 2022 Yanli Liu, Jiming Zhao, Chu-min Li, Hua Jiang, Kun He

Branch-and-Bound (BnB) is the basis of a class of efficient algorithms for MCS, consisting in successively selecting vertices to match and pruning when it is discovered that a solution better than the best solution found so far does not exist.

Reinforcement Learning (RL)

MetaLR: Meta-tuning of Learning Rates for Transfer Learning in Medical Imaging

1 code implementation3 Jun 2022 Yixiong Chen, Li Liu, Jingxian Li, Hua Jiang, Chris Ding, Zongwei Zhou

In this work, we propose a meta-learning-based LR tuner, named MetaLR, to make different layers automatically co-adapt to downstream tasks based on their transferabilities across domains.

Meta-Learning Transfer Learning

Cross-Utterance Conditioned VAE for Non-Autoregressive Text-to-Speech

1 code implementation ACL 2022 Yang Li, Cheng Yu, Guangzhi Sun, Hua Jiang, Fanglei Sun, Weiqin Zu, Ying Wen, Yang Yang, Jun Wang

Modelling prosody variation is critical for synthesizing natural and expressive speech in end-to-end text-to-speech (TTS) systems.

A Deep Learning Approach to Predicting Ventilator Parameters for Mechanically Ventilated Septic Patients

no code implementations21 Feb 2022 Zhijun Zeng, Zhen Hou, Ting Li, Lei Deng, Jianguo Hou, Xinran Huang, Jun Li, Meirou Sun, Yunhan Wang, Qiyu Wu, Wenhao Zheng, Hua Jiang, Qi Wang

We develop a deep learning approach to predicting a set of ventilator parameters for a mechanically ventilated septic patient using a long and short term memory (LSTM) recurrent neural network (RNN) model.

Tie-line Security Regions in High Dimension for Renewable Accommodations

no code implementations4 Jan 2022 Wei Lin, Hua Jiang, Zhifang Yang

However, a tie-line security region is a high-dimension polytope due to multiple time periods and border buses inherently in power system operations, leading to the considerable computational burden.

Vocal Bursts Intensity Prediction

Real space topological invariant and higher-order topological Anderson insulator in two-dimensional non-Hermitian systems

no code implementations24 Feb 2021 Hongfang Liu, Ji-Kun Zhou, Bing-Lan Wu, Zhi-Qiang Zhang, Hua Jiang

We study the characterization and realization of higher-order topological Anderson insulator (HOTAI) in non-Hermitian systems, where the non-Hermitian mechanism ensures extra symmetries as well as gain and loss disorder. We illuminate that the quadrupole moment $Q_{xy}$ can be used as the real space topological invariant of non-Hermitian higher-order topological insulator (HOTI).

Disordered Systems and Neural Networks Mesoscale and Nanoscale Physics

Quantum Spin-Valley Hall Kink States: From Concept to Materials Design

no code implementations11 Feb 2021 Tong Zhou, Shuguang Cheng, Hua Jiang, Zhongqin Yang, Igor Zutic

We propose a general and tunable platform to realize high-density arrays of quantum spin-valley Hall kink (QSVHK) states with spin-valley-momentum locking based on a two-dimensional hexagonal topological insulator.

Mesoscale and Nanoscale Physics Materials Science

A Semi-Grand Canonical Kinetic Monte Carlo study of Single-Walled Carbon Nanotubes growth

no code implementations6 Oct 2020 Georg Daniel Förster, Thomas D. Swinburne, Hua Jiang, Esko Kauppinen, Christophe Bichara

In this contribution, we establish a simple model for the prediction of the growth rates of carbon nanotubes of different chiralities, as a function of energies characterizing the carbon nanotube-catalyst interface and of parameters of the synthesis.

Mesoscale and Nanoscale Physics Statistical Mechanics

A Learning based Branch and Bound for Maximum Common Subgraph Problems

no code implementations15 May 2019 Yan-li Liu, Chu-min Li, Hua Jiang, Kun He

Branch-and-bound (BnB) algorithms are widely used to solve combinatorial problems, and the performance crucially depends on its branching heuristic. In this work, we consider a typical problem of maximum common subgraph (MCS), and propose a branching heuristic inspired from reinforcement learning with a goal of reaching a tree leaf as early as possible to greatly reduce the search tree size. Extensive experiments show that our method is beneficial and outperforms current best BnB algorithm for the MCS.

reinforcement-learning Reinforcement Learning (RL)

Cannot find the paper you are looking for? You can Submit a new open access paper.