Search Results for author: Tao Zhu

Found 12 papers, 4 papers with code

一种非结构化数据表征增强的术后风险预测模型(An Unstructured Data Representation Enhanced Model for Postoperative Risk Prediction)

no code implementations CCL 2022 Yaqiang Wang, Xiao Yang, Xuechao Hao, Hongping Shu, Guo Chen, Tao Zhu

“准确的术后风险预测对临床资源规划和应急方案准备以及降低患者的术后风险和死亡率具有积极作用。术后风险预测目前主要基于术前和术中的患者基本信息、实验室检查、生命体征等结构化数据, 而蕴含丰富语义信息的非结构化术前诊断的价值还有待验证。针对该问题, 本文提出一种非结构化数据表征增强的术后风险预测模型, 利用自注意力机制, 精巧的将结构化数据与术前诊断数据进行信息加权融合。基于临床数据, 将本文方法与术后风险预测常用的统计机器学习模型以及最新的深度神经网络进行对比, 本文方法不仅提升了术后风险预测的性能, 同时也为预测模型带来了良好的可解释性。”

Parameter-efficient Continual Learning Framework in Industrial Real-time Text Classification System

no code implementations NAACL (ACL) 2022 Tao Zhu, Zhe Zhao, Weijie Liu, Jiachi Liu, Yiren Chen, Weiquan Mao, Haoyan Liu, Kunbo Ding, Yudong Li, Xuefeng Yang

Catastrophic forgetting is a challenge for model deployment in industrial real-time systems, which requires the model to quickly master a new task without forgetting the old one.

Continual Learning text-classification +1

A Multi-Task Deep Learning Approach for Sensor-based Human Activity Recognition and Segmentation

no code implementations20 Mar 2023 Furong Duan, Tao Zhu, Jinqiang Wang, Liming Chen, Huansheng Ning, Yaping Wan

Sensor-based human activity segmentation and recognition are two important and challenging problems in many real-world applications and they have drawn increasing attention from the deep learning community in recent years.

Benchmarking Human Activity Recognition

TencentPretrain: A Scalable and Flexible Toolkit for Pre-training Models of Different Modalities

2 code implementations13 Dec 2022 Zhe Zhao, Yudong Li, Cheng Hou, Jing Zhao, Rong Tian, Weijie Liu, Yiren Chen, Ningyuan Sun, Haoyan Liu, Weiquan Mao, Han Guo, Weigang Guo, Taiqiang Wu, Tao Zhu, Wenhang Shi, Chen Chen, Shan Huang, Sihong Chen, Liqun Liu, Feifei Li, Xiaoshuai Chen, Xingwu Sun, Zhanhui Kang, Xiaoyong Du, Linlin Shen, Kimmo Yan

The proposed pre-training models of different modalities are showing a rising trend of homogeneity in their model structures, which brings the opportunity to implement different pre-training models within a uniform framework.

A Simple and Effective Method to Improve Zero-Shot Cross-Lingual Transfer Learning

1 code implementation COLING 2022 Kunbo Ding, Weijie Liu, Yuejian Fang, Weiquan Mao, Zhe Zhao, Tao Zhu, Haoyan Liu, Rong Tian, Yiren Chen

Existing zero-shot cross-lingual transfer methods rely on parallel corpora or bilingual dictionaries, which are expensive and impractical for low-resource languages.

text-classification Text Classification +3

Multi-scale Attentive Image De-raining Networks via Neural Architecture Search

1 code implementation2 Jul 2022 Lei Cai, Yuli Fu, Wanliang Huo, Youjun Xiang, Tao Zhu, Ying Zhang, Huanqiang Zeng, Delu Zeng

The proposed method formulates a new multi-scale attention search space with multiple flexible modules that are favorite to the image de-raining task.

Neural Architecture Search Rain Removal

Negative Selection by Clustering for Contrastive Learning in Human Activity Recognition

no code implementations23 Mar 2022 Jinqiang Wang, Tao Zhu, Liming Chen, Huansheng Ning, Yaping Wan

Compared with SimCLR, it redefines the negative pairs in the contrastive loss function by using unsupervised clustering methods to generate soft labels that mask other samples of the same cluster to avoid regarding them as negative samples.

Contrastive Learning Human Activity Recognition +1

Semantic Matching from Different Perspectives

1 code implementation14 Feb 2022 Weijie Liu, Tao Zhu, Weiquan Mao, Zhe Zhao, Weigang Guo, Xuefeng Yang, Qi Ju

In this paper, we pay attention to the issue which is usually overlooked, i. e., \textit{similarity should be determined from different perspectives}.

Text Matching text similarity

Sensor Data Augmentation by Resampling for Contrastive Learning in Human Activity Recognition

no code implementations5 Sep 2021 Jinqiang Wang, Tao Zhu, Jingyuan Gan, Liming Chen, Huansheng Ning, Yaping Wan

The experiment results show that the resampling augmentation method outperforms all state-of-the-art methods under a small amount of labeled data, on SimCLRHAR and MoCoHAR, with mean F1-score as the evaluation metric.

Contrastive Learning Data Augmentation +1

Dynamical Polarizability of Graphene with Spatial Dispersion

no code implementations9 Jan 2021 Tao Zhu, Mauro Antezza, Jian-Sheng Wang

We perform a detailed analysis of electronic polarizability of graphene with different theoretical approaches.

Mesoscale and Nanoscale Physics Materials Science

Interpretable Set Functions

no code implementations31 May 2018 Andrew Cotter, Maya Gupta, Heinrich Jiang, James Muller, Taman Narayan, Serena Wang, Tao Zhu

We propose learning flexible but interpretable functions that aggregate a variable-length set of permutation-invariant feature vectors to predict a label.

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