Search

Your search keyword '"Liu, Jiayi"' showing total 2,345 results
Start Over Author "Liu, Jiayi"
2,345 results on '"Liu, Jiayi"'

204. Integration Of Solution‐Processed BaTiO3 Thin Films with High Pockels Coefficient on Photonic Platforms

Author

Picavet, Ewout, primary, Lievens, Enes, additional, De Geest, Kobe, additional, Rijckaert, Hannes, additional, Fernandez, Edgar Gutierrez, additional, Bikondoa, Oier, additional, Solano, Eduardo, additional, Paturi, Petriina, additional, Singh, Nishant, additional, Pannier, Tinus, additional, Liu, Jiayi, additional, Yin, Xin, additional, Van Thourhout, Dries, additional, Beeckman, Jeroen, additional, and De Buysser, Klaartje, additional

Published
2024
Full Text
View/download PDF

205. Stereotactic central/core ablative radiation therapy: results of a phase I study of a novel strategy to treat bulky tumor

Author

Yang, Jun, primary, Lu, Qiuxia, additional, Qi, Weihua, additional, Kolb, Ryann D., additional, Wang, Lei, additional, Li, Yuan, additional, Li, Sida, additional, Lin, Yihui, additional, Liu, Jiayi, additional, Mourad, Waleed, additional, MirkhaghaniHaghighi, Farzaneh, additional, Slavisa, Tubin, additional, Wu, Xiaodong, additional, You, Wei-Ciang, additional, Yang, Eddy, additional, Hanlon, Alex, additional, Zhu, Alan, additional, and Yan, Weisi, additional

Published
2024
Full Text
View/download PDF

207. Assessing the Risk of Bias in Randomized Clinical Trials With Large Language Models

Author

Lai, Honghao, primary, Ge, Long, additional, Sun, Mingyao, additional, Pan, Bei, additional, Huang, Jiajie, additional, Hou, Liangying, additional, Yang, Qiuyu, additional, Liu, Jiayi, additional, Liu, Jianing, additional, Ye, Ziying, additional, Xia, Danni, additional, Zhao, Weilong, additional, Wang, Xiaoman, additional, Liu, Ming, additional, Talukdar, Jhalok Ronjan, additional, Tian, Jinhui, additional, Yang, Kehu, additional, and Estill, Janne, additional

Published
2024
Full Text
View/download PDF

220. Make (Nearly) Every Neural Network Better: Generating Neural Network Ensembles by Weight Parameter Resampling

Author

Liu, Jiayi, Tripathi, Samarth, Kurup, Unmesh, and Shah, Mohak

Subjects
Computer Science - Machine Learning, Computer Science - Artificial Intelligence, Computer Science - Computer Vision and Pattern Recognition, Statistics - Machine Learning
Abstract

Deep Neural Networks (DNNs) have become increasingly popular in computer vision, natural language processing, and other areas. However, training and fine-tuning a deep learning model is computationally intensive and time-consuming. We propose a new method to improve the performance of nearly every model including pre-trained models. The proposed method uses an ensemble approach where the networks in the ensemble are constructed by reassigning model parameter values based on the probabilistic distribution of these parameters, calculated towards the end of the training process. For pre-trained models, this approach results in an additional training step (usually less than one epoch). We perform a variety of analysis using the MNIST dataset and validate the approach with a number of DNN models using pre-trained models on the ImageNet dataset., Comment: Accepted at UAI Workshop on Uncertainty in Deep Learning

Published
2018

221. Effective Building Block Design for Deep Convolutional Neural Networks using Search

Author

Dutta, Jayanta K, Liu, Jiayi, Kurup, Unmesh, and Shah, Mohak

Subjects
Computer Science - Learning, Computer Science - Artificial Intelligence, Computer Science - Computer Vision and Pattern Recognition, Statistics - Machine Learning
Abstract

Deep learning has shown promising results on many machine learning tasks but DL models are often complex networks with large number of neurons and layers, and recently, complex layer structures known as building blocks. Finding the best deep model requires a combination of finding both the right architecture and the correct set of parameters appropriate for that architecture. In addition, this complexity (in terms of layer types, number of neurons, and number of layers) also present problems with generalization since larger networks are easier to overfit to the data. In this paper, we propose a search framework for finding effective architectural building blocks for convolutional neural networks (CNN). Our approach is much faster at finding models that are close to state-of-the-art in performance. In addition, the models discovered by our approach are also smaller than models discovered by similar techniques. We achieve these twin advantages by designing our search space in such a way that it searches over a reduced set of state-of-the-art building blocks for CNNs including residual block, inception block, inception-residual block, ResNeXt block and many others. We apply this technique to generate models for multiple image datasets and show that these models achieve performance comparable to state-of-the-art (and even surpassing the state-of-the-art in one case). We also show that learned models are transferable between datasets.

Published
2018

248. Extracellular Vesicles: A New Star for Gene Drug Delivery

Author

Sun,Man, Zhang,Huan, Liu,Jiayi, Chen,Jiayi, Cui,Yaxin, Wang,Simiao, Zhang,Xiangyu, Yang,Zhaogang, Sun,Man, Zhang,Huan, Liu,Jiayi, Chen,Jiayi, Cui,Yaxin, Wang,Simiao, Zhang,Xiangyu, and Yang,Zhaogang

Abstract

Man Sun,1 Huan Zhang,1 Jiayi Liu,1 Jiayi Chen,1 Yaxin Cui,1 Simiao Wang,1 Xiangyu Zhang,2 Zhaogang Yang1 1School of Life Sciences, Jilin University, Changchun, 130012, People’s Republic of China; 2Department of General Surgery, Sir Run Run Shaw Hospital, College of Medicine, Zhejiang University, Hangzhou, 310020, People’s Republic of ChinaCorrespondence: Xiangyu Zhang; Zhaogang Yang, Tel/Fax +86-431-85155320, Email 3314023@zju.edu.cn; zhaogangyang@jlu.edu.cnAbstract: Recently, gene therapy has become a subject of considerable research and has been widely evaluated in various disease models. Though it is considered as a stand-alone agent for COVID-19 vaccination, gene therapy is still suffering from the following drawbacks during its translation from the bench to the bedside: the high sensitivity of exogenous nucleic acids to enzymatic degradation; the severe side effects induced either by exogenous nucleic acids or components in the formulation; and the difficulty to cross the barriers before reaching the therapeutic target. Therefore, for the successful application of gene therapy, a safe and reliable transport vector is urgently needed. Extracellular vesicles (EVs) are the ideal candidate for the delivery of gene drugs owing to their low immunogenicity, good biocompatibility and low toxicity. To better understand the properties of EVs and their advantages as gene drug delivery vehicles, this review covers from the origin of EVs to the methods of EVs generation, as well as the common methods of isolation and purification in research, with their pros and cons discussed. Meanwhile, the engineering of EVs for gene drugs is also highlighted. In addition, this paper also presents the progress in the EVs-mediated delivery of microRNAs, small interfering RNAs, messenger RNAs, plasmids, and antisense oligonucleotides. We believe this review will provide a theoretical basis for the development of gene drugs.Keywords: extracellular vesicles, gene therapy, drug delivery s

Published
2024

Catalog

Books, media, physical & digital resources
See catalog results