检索结果-内蒙古大学图书馆

Bridging explicit and implicit deep generative models via neural Stein estimators

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Wu, Qitian Gao, Rui Zha, Hongyuan Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University University of Texas Austin United States School of Data Science Shenzhen Institute of Artificial Intelligence and Robotics for Society The Chinese University of Hong Kong Shenzhen Hong Kong The Chinese University of Hong Kong Shenzhen China

There are two types of deep generative models: explicit and implicit. The former defines an explicit density form that allows likelihood inference;while the latter targets a flexible transformation from random noise to generated samples. While the two classes of generative models have shown great power in many applications, both of them, when used alone, suffer from respective limitations and drawbacks. To take full advantages of both models and enable mutual compensation, we propose a novel joint training framework that bridges an explicit (unnormalized) density estimator and an implicit sample generator via Stein discrepancy. We show that our method 1) induces novel mutual regularization via kernel Sobolev norm penalization and Moreau-Yosida regularization, and 2) stabilizes the training dynamics. Empirically, we demonstrate that proposed method can facilitate the density estimator to more accurately identify data modes and guide the generator to output higher-quality samples, comparing with training a single counterpart. The new approach also shows promising results when the training samples are contaminated or limited. © 2019, CC BY.

关键词：

Judging chemical reaction practicality from positive sample only learning

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Jiang, Shu Zhang, Zhuosheng Zhao, Hai Li, Jiangtong Yang, Yang Lu, Bao-Liang Xia, Ning Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai200240 China Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University Shanghai200240 China College of Zhiyuan Shanghai Jiao Tong University Shanghai200240 China Chemical.AI Shanghai200240 China

Chemical reaction practicality is the core task among all symbol intelligence based chemical information processing, for example, it provides indispensable clue for further automatic synthesis route inference. Considering that chemical reactions have been represented in a language form, we propose a new solution to generally judge the practicality of organic reaction without considering complex quantum physical modeling or chemistry knowledge. While tackling the practicality judgment as a machine learning task from positive and negative (chemical reaction) samples, all existing studies have to carefully handle the serious insufficiency issue on the negative samples. We propose an auto-construction method to well solve the extensively existed long-term difficulty. Experimental results show our model can effectively predict the practicality of chemical reactions, which achieves a high accuracy of 99.76% on real large-scale chemical lab reaction practicality judgment. Copyright © 2019, The Authors. All rights reserved.

关键词： Chemical reactions

BraTS-PEDs: Results of the Multi-Consortium International Pediatric Brain Tumor Segmentation Challenge 2023

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Kazerooni, Anahita Fathi Khalili, Nastaran Liu, Xinyang Haldar, Debanjan Jiang, Zhifan Zapaishchykova, Anna Pavaine, Julija Shah, Lubdha M. Jones, Blaise V. Sheth, Nakul Prabhu, Sanjay P. McAllister, Aaron S. Tu, Wenxin Nandolia, Khanak K. Rodriguez, Andres F. Shaikh, Ibraheem Salman Sanchez-Montano, Mariana Lai, Hollie Anne Adewole, Maruf Albrecht, Jake Anazodo, Udunna Anderson, Hannah Anwar, Syed Muhammed Aristizabal, Alejandro Bagheri, Sina Baid, Ujjwal Bergquist, Timothy Borja, Austin J. Calabrese, Evan Chung, Verena Conte, Gian-Marco Eddy, James Ezhov, Ivan Familiar, Ariana M. Farahani, Keyvan Gandhi, Deep Gottipati, Anurag Haldar, Shuvanjan Iglesias, Juan Eugenio Janas, Anastasia Elaine, Elaine Karargyris, Alexandros Kassem, Hasan Khalili, Neda Kofler, Florian LaBella, Dominic Van Leemput, Koen Li, Hongwei B. Maleki, Nazanin Meier, Zeke Menze, Bjoern Moawad, Ahmed W. Pati, Sarthak Piraud, Marie Poussaint, Tina Reitman, Zachary J. Rudie, Jeffrey D. Saluja, Rachit Sheller, MIcah Shinohara, Russell Takeshi Viswanathan, Karthik Wang, Chunhao Wiestler, Benedikt Wiggins, Walter F. Davatzikos, Christos Storm, Phillip B. Bornhorst, Miriam Packer, Roger Hummel, Trent de Blank, Peter Hoffman, Lindsey Aboian, Mariam Nabavizadeh, Ali Ware, Jeffrey B. Kann, Benjamin H. Rood, Brian Resnick, Adam Bakas, Spyridon Vossough, Arastoo Linguraru, Marius George The Children’s Hospital of Philadelphia PA United States Sheikh Zayed Institute for Pediatric Surgical Innovation Children’s National Hospital WashingtonDC United States Department of Neurosurgery Thomas Jefferson University Hospital PA United States Dana-Farber Brigham Cancer Center Boston Children’s Hospital BostonMA United States Department of Paediatric Radiology Royal Manchester Children’s Hospital Manchester University Hospitals NHS Foundation Trust University of Manchester Manchester United Kingdom University of Utah UT United States Cincinnati Children’s Hospital Medical Center OH United States Department of Radiology The Children’s Hospital of Philadelphia PA United States Division of Neuroradiology Department of Radiology Boston Children’s Hospital Harvard Medical School BostonMA United States Department of Radiology Nationwide Children’s Hospital OH United States College of Arts and Sciences University of Pennsylvania PA United States Department of Diagnostic and Interventional Radiology All India Institute of Medical Sciences Rishikesh India Department of Diagnostic & Interventional Imaging Neuroradiology Section The University of Texas Health HoustonTX United States Beth Israel Deaconess Medical Center Harvard Medical School MA United States Unidad de Patologia Clinica:Guadalajara Jalisco Mexico Department of Radiology Children’s Health Orange County CA United States Lab Crestview Radiology Lagos Nigeria Sage Bionetworks United States McGill University MontrealQC Canada Department of Radiology Perelman School of Medicine University of Pennsylvania PhiladelphiaPA United States MLCommons United States Division of Computational Pathology Department of Pathology and Laboratory Medicine Indiana University School of Medicine IndianapolisIN United States Department of Neurosurgery The University of Southern California CA United States Department of Radiology Duke University Medical Center DurhamNC United States Mayo Clinic MN

Pediatric central nervous system tumors are the leading cause of cancer-related deaths in children. The five-year survival rate for high-grade glioma in children is less than 20%. The development of new treatments is dependent upon multi-institutional collaborative clinical trials requiring reproducible and accurate centralized response assessment. We present the results of the BraTS-PEDs 2023 challenge, the first Brain Tumor Segmentation (BraTS) challenge focused on pediatric brain tumors. This challenge utilized data acquired from multiple international consortia dedicated to pediatric neuro-oncology and clinical trials. BraTS-PEDs 2023 aimed to evaluate volumetric segmentation algorithms for pediatric brain gliomas from magnetic resonance imaging using standardized quantitative performance evaluation metrics employed across the BraTS 2023 challenges. The top-performing ai approaches for pediatric tumor analysis included ensembles of nnU-Net and Swin UNETR, Auto3DSeg, or nnU-Net with a self-supervised framework. The BraTS-PEDs 2023 challenge fostered collaboration between clinicians (neuro-oncologists, neuroradiologists) and ai/imaging scientists, promoting faster data sharing and the development of automated volumetric analysis techniques. These advancements could significantly benefit clinical trials and improve the care of children with brain tumors. © 2024, CC BY.

关键词： Pediatrics

Personalized Behavior Prediction with Encoder-to-Decoder Structure

学校读者我要写书评

暂无评论

Personalized Behavior Prediction with Encoder-to-Decoder Str...

International Conference on Networking, Architecture, and Storage (NAS)

作者： Tong Yin Xiaotie Deng Yuan Qi Wei Chu Jing Pan Xiang Yan Junwu Xiong Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China School of Electronics Engineering and Computer Science Peking University Peking China AI Department Ant Financial Services Group Hangzhou China

ISBN: (纸本)9781538683682

With the rise of the Internet industry and the technique of artificial intelligence, personalized services are increasingly important in recent years for improving user experience and increasing corporates' competitiveness and profits. Precise prediction of customers' behaviors has shown great effects in modern business marketing, especially when making personalized decisions. In this paper, we develop a deep learning network to make personalized predictions of their behaviors among a list of potential choices. The architecture of this model combines each user's features and his historical event lists by sequence-to-sequence (Seq2Seq) structure and make predictions based on his recent event lists. We also modify the long-short- term memory (LSTM) cell forget gate's structure to enhance the attention ability. Such design, called the attetioned LSTM, converges quicker and better while still maintain the similar performance in open dataset IMDB. In addition, in dealing with personalized prediction problems in real-world datasets provided by our cooperative company, our attentioned LSTM achieves a 10% higher precision in average than the standard LSTM model. The advantage is confirmed in evaluation of this generic method on a real dataset of users' behaviors sequences and individuals' attribute profiles from Ant Financial. It also achieves a great result working on the real-world business scene. This model can also achieve a great performance working on the real-world business scene.

关键词： Decoding Companies Predictive models computer architecture Logic gates

Translating a math word problem to an expression tree

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Wang, Lei Wang, Yan Cai, Deng Zhang, Dongxiang Liu, Xiaojiang Center for Future Media School of Computer Science and Engineering Uestc Tencent Ai Lab Department of Systems Engineering and Engineering Management Chinese University of Hong Kong

Sequence-to-sequence (SEQ2SEQ) models have been successfully applied to automatic math word problem solving. Despite its simplicity, a drawback still remains: a math word problem can be correctly solved by more than one equations. This non-deterministic transduction harms the performance of maximum likelihood estimation. In this paper, by considering the uniqueness of expression tree, we propose an equation normalization method to normalize the duplicated equations. Moreover, we analyze the performance of three popular SEQ2SEQ models on the math word problem solving. We find that each model has its own specialty in solving problems, consequently an ensemble model is then proposed to combine their advantages. Experiments on dataset Math23K show that the ensemble model with equation normalization significantly outperforms the previous state-of-the-art methods. Copyright © 2018, The Authors. All rights reserved.

关键词： Maximum likelihood estimation

Author Correction: Federated deep learning for detecting COVID-19 lung abnormalities in CT: a privacy-preserving multinational validation study

学校读者我要写书评

暂无评论

NPJ digital medicine 2022年第1期5卷 56页

作者： Qi Dou Tiffany Y So Meirui Jiang Quande Liu Varut Vardhanabhuti Georgios Kaissis Zeju Li Weixin Si Heather H C Lee Kevin Yu Zuxin Feng Li Dong Egon Burian Friederike Jungmann Rickmer Braren Marcus Makowski Bernhard Kainz Daniel Rueckert Ben Glocker Simon C H Yu Pheng Ann Heng Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong SAR China. qdou@cse.cuhk.edu.hk. Department of Imaging and Interventional Radiology The Chinese University of Hong Kong Hong Kong SAR China. Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong SAR China. Department of Diagnostic Radiology Li Ka Shing Faculty of Medicine The University of Hong Kong Hong Kong SAR China. Biomedical Image Analysis Group Imperial College London London UK. Institute for Diagnostic and Interventional Radiology Technical University of Munich School of Medicine Munich Germany. OpenMined Oxford UK. Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen Guangdong China. Department of Diagnostic Radiology Princess Margaret Hospital Hong Kong SAR China. Department of Radiology Tuen Muen Hospital Hong Kong SAR China. Department of Emergency Medicine Peking University ShenZhen Hospital Shenzhen Guangdong China. Department of Radiology Zhijiang People's Hospital Zhijiang Hubei China. German Cancer Research Center (DKFZ) Heidelberg Germany. AI in Medicine and Healthcare Technical University of Munich School of Informatics and Medicine Munich Germany. Biomedical Image Analysis Group Imperial College London London UK. b.glocker@imperial.ac.uk. Department of Imaging and Interventional Radiology The Chinese University of Hong Kong Hong Kong SAR China. simonyu@cuhk.edu.hk. Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong SAR China. pheng@cse.cuhk.edu.hk.

Customer behavioural modelling of order cancellation in coupled ride-sourcing and taxi markets

学校读者我要写书评

暂无评论

Transportation Research Procedia 2019年 38卷 853-873页

作者： Xiaolei Wang Wei Liu Hai Yang Dan Wang Jieping Ye School of Economics and Management Tongji University Shanghai P.R. China School of Computer Science and Engineering University of New South Wales Sydney NSW 2052 Australia Research Centre for Integrated Transport Innovation School of Civil and Environmental Engineering University of New South Wales Sydney NSW 2052 Australia Department of Civil and Environmental Engineering The Hong Kong University of Science and Technology Clear Water Bay Kowloon Hong Kong P.R. China AI Labs Didi Chuxing West Road Haidian District Beijing P.R. China

Today massive on-demand ride requests are dispatched every hour on ride-sourcing platforms, but an unneglectable amount of confirmed orders is later cancelled by customers. Customers’ order cancellation not only wastes drivers’ efforts, but also lowers the availability of supplies on the ride-sourcing platform. Based on a two-month hourly-average dataset provided by Didi Chuxing, this paper makes the first attempt to look into customers’ cancellation behaviours of the confirmed-orders. The customers’ confirmed-order cancellation rate (COCR) is observed to be significantly and negatively correlated to the customers’ waiting time for pick-up time. We regard such counter-intuitive phenomena as an outcome of customers’ mode switch upon meeting vacant taxis while in waiting for ride-sourcing vehicles. The cancellation rate is thus characterized as a function of customers’ average waiting time for ride-sourcing vehicles and cruising taxis, the platform’s penalty strategy for cancellation of confirmed-orders, and the customers’ own characteristics (i.e., value of time, psychological cost of order cancellation). As both the customers’ waiting times for ride-sourcing vehicles and cruising taxis are endogenously determined by the demand and supply of ride-sourcing and taxi markets respectively, a system of nonlinear equations is proposed to depict the complex interactions between the two markets at equilibrium while considering customers’ order cancellation behaviour under a given penalty and compensation rule. With the proposed model, we theoretically establish the existence of the equilibrium under mild conditions, and examine the optimal pricing and penalty/compensation strategies that respectively maximize the platform’s profit and social welfare respectively. Numerical examples are presented to demonstrate the distinct optimal pricing and penalty/compensation strategies for different objectives and examine the various impacts of the social credibility.

关键词： ride-sourcing taxi order cancellation equilibrium

Deep extractor network for target speaker recovery from single channel speech mixtures

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Wang, Jun Chen, Jie Su, Dan Chen, Lianwu Yu, Meng Qian, Yanmin Yu, Dong Tencent AI Lab Shenzhen China Tencent AI Lab BellevueWA United States Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China

Speaker-aware source separation methods are promising workarounds for major difficulties such as arbitrary source permutation and unknown number of sources. However, it remains challenging to achieve satisfying performance provided a very short available target speaker utterance (anchor). Here we present a novel"deep extractor network" which creates an extractor point for the target speaker in a canonical high dimensional embedding space, and pulls together the time-frequency bins corresponding to the target speaker. The proposed model is different from prior works in that the canonical embedding space encodes knowledges of both the anchor and the mixture during an end-to-end training phase: First, embeddings for the anchor and mixture speech are separately constructed in a primary embedding space, and then combined as an input to feed-forward layers to transform to a canonical embedding space which we discover more stable than the primary one. Experimental results show that given a very short utterance, the proposed model can efficiently recover high quality target speech from a mixture, which outperforms various baseline models, with 5.2% and 6.6% relative improvements in SDR and PESQ respectively compared with a baseline oracle deep attracor model. Meanwhile, we show it can be generalized well to more than one interfering speaker. Copyright © 2018, The Authors. All rights reserved.

关键词： Embeddings

Beyond Low Earth Orbit: Biomonitoring, Artificial Intelligence, and Precision Space Health

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Scott, Ryan T. Antonsen, Erik L. Sanders, Lauren M. Hastings, Jaden J.A. Park, Seung-Min Mackintosh, Graham Reynolds, Robert J. Hoarfrost, Adrienne L. Sawyer, Aenor Greene, Casey S. Glicksberg, Benjamin S. Theriot, Corey A. Berrios, Daniel C. Miller, Jack Babdor, Joel Barker, Richard Baranzini, Sergio E. Beheshti, Afshin Chalk, Stuart Delgado-Aparicio, Guillermo M. Haendel, Melissa Hamid, Arif A. Heller, Philip Jamieson, Daniel Jarvis, Katelyn J. Kalantari, John Khezeli, Kia Komarova, Svetlana V. Komorowski, Matthieu Kothiyal, Prachi Mahabal, Ashish Manor, Uri Martin, Hector Garcia Mason, Christopher E. Matar, Mona Mias, George I. Myers, Jerry G. Nelson, Charlotte Oribello, Jonathan Parsons-Wingerter, Patricia Prabhu, R.K. Qutub, Amina Ann Rask, Jon Saravia-Butler, Amanda Saria, Suchi Singh, Nitin Kumar Soboczenski, Frank Snyder, Michael Soman, Karthik van Valen, David Venkateswaran, Kasthuri Warren, Liz Worthey, Liz Yang, Jason H. Zitnik, Marinka Costes, Sylvain V. KBR Space Biosciences Division NASA Ames Research Center Moffett FieldCA94035 United States Department of Emergency Medicine Center for Space Medicine Baylor College of Medicine HoustonTX77030 United States Blue Marble Space Institute of Science Space Biosciences Division NASA Ames Research Center Moffett FieldCA94035 United States Department of Physiology and Biophysics Weill Cornell Medicine New YorkNY10065 United States Department of Urology Department of Radiology Stanford University School of Medicine StanfordCA94305 United States Bay Area Environmental Research Institute NASA Ames Research Center Moffett FieldCA94035 United States Mortality Research & Consulting Inc. HoustonTX77058 United States Space Biosciences Division NASA Ames Research Center Moffett FieldCA94035 United States UC Space Health Department of Orthopaedic Surgery University of California San Francisco San FranciscoCA94143 United States Center for Health AI Department of Biochemistry and Molecular Genetics University of Colorado School of Medicine Anschutz Medical Campus AuroraCO80045 United States Hasso Plattner Institute for Digital Health at Mount Sinai Department of Genetics and Genomic Sciences Icahn School of Medicine at Mount Sinai New YorkNY10065 United States Department of Preventive Medicine and Community Health UTMB GalvestonTX77551 United States Human Health and Performance Directorate NASA Johnson Space Center HoustonTX77058 United States Department of Microbiology and Immunology Department of Otolaryngology Head and Neck Surgery University of California San Francisco San FranciscoCA94143 United States The Gilroy AstroBiology Research Group The University of Wisconsin Madison MadisonWI53706 United States Weill Institute for Neurosciences Department of Neurology University of California San Francisco San FranciscoCA94158 United States Department of Chemistry University of North Florida JacksonvilleFL32224 United States Data Scienc

Human space exploration beyond low Earth orbit will involve missions of significant distance and duration. To effectively mitigate myriad space health hazards, paradigm shifts in data and space health systems are necessary to enable Earth-independence, rather than Earth-reliance. Promising developments in the fields of artificial intelligence and machine learning for biology and health can address these needs. We propose an appropriately autonomous and intelligent Precision Space Health system that will monitor, aggregate, and assess biomedical statuses;analyze and predict personalized adverse health outcomes;adapt and respond to newly accumulated data;and provide preventive, actionable, and timely insights to individual deep space crew members and iterative decision support to their crew medical officer. Here we present a summary of recommendations from a workshop organized by the National Aeronautics and Space Administration, on future applications of artificial intelligence in space biology and health. In the next decade, biomonitoring technology, biomarker science, spacecraft hardware, intelligent software, and streamlined data management must mature and be woven together into a Precision Space Health system to enable humanity to thrive in deep space. © 2021, CC BY.

关键词： Earth (planet)