检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Osterhoudt, Hunter Schneider, Courtney E. Mohammad, Haneef A. Shih, Minmei Harper, Alexandra E. Zhou, Leming Skidmore, Elizabeth R. Wang, Yanshan Department of Computer Science School of Computing and Information University of Pittsburgh United States Department of Occupational Therapy School of Health and Rehabilitation Sciences University of Pittsburgh United States Department of Information Science School of Computing and Information University of Pittsburgh United States Department of Health Information Management School of Health and Rehabilitation Sciences University of Pittsburgh United States Department of Biomedical Informatics University of Pittsburgh PittsburghPA United States Intelligent Systems Program University of Pittsburgh PittsburghPA United States

Strategy training is a multidisciplinary rehabilitation approach that teaches skills to reduce disability among those with cognitive impairments following a stroke. Strategy training has been shown in randomized, controlled clinical trials to be a more feasible and efficacious intervention for promoting independence than traditional rehabilitation approaches. A standardized fidelity assessment is used to measure adherence to treatment principles by examining guided and directed verbal cues in video recordings of rehabilitation sessions. Although the fidelity assessment for detecting guided and directed verbal cues is valid and feasible for single-site studies, it can become labor intensive, time consuming, and expensive in large, multi-site pragmatic trials. To address this challenge to widespread strategy training implementation, we leveraged natural language processing (NLP) techniques to automate the strategy training fidelity assessment, i.e., to automatically identify guided and directed verbal cues from video recordings of rehabilitation sessions. We developed a rule-based NLP algorithm, a long-short term memory (LSTM) model, and a bidirectional encoder representation from transformers (BERT) model for this task. The best performance was achieved by the BERT model with a 0.8075 F1-score. This BERT model was verified on an external validation dataset collected from a separate major regional health system and achieved an F1 score of 0.8259, which shows that the BERT model generalizes well. The findings from this study hold widespread promise in psychology and rehabilitation intervention research and practice. Copyright © 2022, The Authors. All rights reserved.

关键词： Video recording

来源：评论

学校读者我要写书评

暂无评论

Instruction Multi-Constraint Molecular Generation Using a Teacher-Student Large Language Model

arXiv

引用

arXiv 2024年

作者： Zhou, Peng Wang, Jianmin Li, Chunyan Wang, Zixu Liu, Yiping Sun, Siqi Lin, Jianxin Wei, Leyi Cai, Xibao Lai, Houtim Liu, Wei Wang, Longyue Liu, Yuansheng Zeng, Xiangxiang College of Information Science and Engineering Hunan University Changsha China The Interdisciplinary Graduate Program in Integrative Biotechnology Yonsei University Incheon21983 Korea Republic of School of Informatics Yunnan Normal University Kunming650500 China Department of Computer Science University of Tsukuba Tsukuba3058577 Japan Research Institute of Intelligent Complex Systems Fudan University Shanghai200433 China Shanghai AI Laboratory Shanghai200232 China Centre for Artificial Intelligence driven Drug Discovery Faculty of Applied Science Macao Polytechnic University China School of Informatics Xiamen University Xiamen China Tencent AI Lab China

While various models and computational tools have been proposed for structure and property analysis of molecules, generating molecules that conform to all desired structures and properties remains a challenge. Here, we introduce a multi-constraint molecular generation large language model, TSMMG, which, akin to a student, incorporates knowledge from various small models and tools, namely, the 'teachers'. To train TSMMG, we construct a large set of text-molecule pairs by extracting molecular knowledge from these 'teachers', enabling it to generate novel molecules that conform to the descriptions through various text prompts. We experimentally show that TSMMG remarkably performs in generating molecules meeting complex, natural language-described property requirements across two-, three-, and four-constraint tasks, with an average molecular validity of over 99% and success ratio of 82.58%, 68.03%, and 67.48%, respectively. The model also exhibits adaptability through zero-shot testing, creating molecules that satisfy combinations of properties that have not been encountered. It can comprehend text inputs with various language styles, extending beyond the confines of outlined prompts, as confirmed through empirical validation. Additionally, the knowledge distillation feature of TSMMG contributes to the continuous enhancement of small models, while the innovative approach to dataset construction effectively addresses the issues of data scarcity and quality, which positions TSMMG as a promising tool in the domains of drug discovery and materials science. Copyright © 2024, The Authors. All rights reserved.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Bayesian group factor analysis with structured sparsity

The Journal of Machine Learning Research

引用

The Journal of Machine Learning Research 2016年第1期17卷

作者： Kevin Murphy Bernhard Schölkopf Shiwen Zhao Chuan Gao Sayan Mukherjee Barbara E. Engelhardt Google MPI for Intelligent Systems Computational Biology and Bioinformatics Program Department of Statistical Science Duke University Durham NC Department of Statistical Science Duke University Durham NC Departments of Statistical Science Computer Science Mathematics Duke University Durham NC Department of Computer Science Center for Statistics and Machine Learning Princeton University Princeton NJ

Latent factor models are the canonical statistical tool for exploratory analyses of low-dimensional linear structure for a matrix of p features across n samples. We develop a structured Bayesian group factor analysis model that extends the factor model to multiple coupled observation matrices; in the case of two observations, this reduces to a Bayesian model of canonical correlation analysis. Here, we carefully define a structured Bayesian prior that encourages both element-wise and column-wise shrinkage and leads to desirable behavior on high-dimensional data. In particular, our model puts a structured prior on the joint factor loading matrix, regularizing at three levels, which enables element-wise sparsity and unsupervised recovery of latent factors corresponding to structured variance across arbitrary subsets of the observations. In addition, our structured prior allows for both dense and sparse latent factors so that covariation among either all features or only a subset of features can be recovered. We use fast parameter-expanded expectation-maximization for parameter estimation in this model. We validate our method on simulated data with substantial structure. We show results of our method applied to three high-dimensional data sets, comparing results against a number of state-of-the-art approaches. These results illustrate useful properties of our model, including i) recovering sparse signal in the presence of dense effects; ii) the ability to scale naturally to large numbers of observations; iii) flexible observation- and factor-specific regularization to recover factors with a wide variety of sparsity levels and percentage of variance explained; and iv) tractable inference that scales to modern genomic and text data sizes.

关键词： bayesian structured sparsity canonical correlation analysis mixture models parameter expansion sparse and low-rank matrix decomposition sparse priors

来源：评论

学校读者我要写书评

暂无评论

A DISTRIBUTED MEDIA ACCESS PROTOCOL FOR PACKET RADIO NETWORKS AND PERFORMANCE ANALYSIS .2. NETWORK SET-UP TIME AND DATA RATE

引用

INTERNATIONAL JOURNAL OF COMMUNICATION systems 1995年第1期8卷 49-63页

作者： POND, LC LI, VOK Communication Sciences Electrical Engineering Systems University of Southern California Los Angeles CA 90089-2565 U.S.A. Lawrence C. Pond received the M.Sc. and Ph.D. degrees in electrical engineering from the University of Southern California in 1983 and 1990 respectively. Dr. Pond is currently a scientist at Hughes Space and Communications Company having joined in 1980. He has worked in the fields of communication system design mobile communication network and spacecraft payload design. He is currently working on the development of satellite-based ATM transport and switching architectures for BISDN and Defense Information System Network amlications. Dr. Pond is a member of IEEE. Victor O. K. Li was born in Hong Kong in 1954. He received his SB SM and Sc.D. degrees in Electrical Engineering and Computer Science from the Massachusetts Institute of Technology Cambridge Massachusetts in 1977 1979 and 1981 respectively. Since February 1981 he has been with the University of Southern California (USC) LOS Angeles California where he is Professor of Electrical Engineering and Director of the USC Communication Sciences Institute. He has published 150 technical papers and has lectured and consulted extensively around the world. His research interests include high-speed communication networks personal communication networks intelligent networks distributed databases queueing theory graph theory and applied probability. Dr. Li is very active in the Institute of Electrical and Electronic Engineers (IEEE) having been a member of the Computer Communications Technical Committee since 1983 and having served as Chairman from 1987–1989. He served as Chairman of the Los Angeles Chapter of the IEEE Information Theory Group from 1983–1985. He is the Steering Committee Chair of the International Conference on Computer Communications and Networks (IC3 N) General Chair of the 1st Annual IC3N held in San Diego California in June 1992 General Chair and Technical Program Chair of the 4th IEEE Workshop on Comp

In this, the second part of a two-part paper, the required time for establishing a mobile packet radio network using the virtual circuit and time division multiple access protocol developed in Part 1 is analysed. Tools are developed to determine the virtual circuit and network set-up times in terms of the channel bandwidth allocated to establish and maintain the network. The tools are then extended to include the effects of user mobility. Then these results are combined with the network capacity results of Part 1 to analyse the trade-off between the data rate and set-up time of the network. Next a hierarchical architecture is proposed and the network data rate versus set-up time trade-off of this architecture is analysed using these tools. This architecture is shown to both provide a higher data rate and establish faster than flat networks of the same number of nodes.

关键词： PACKET RADIO NETWORK EPLRS DISTRIBUTED NETWORK TDMA VIRTUAL CIRCUITS MULTIHOP NETWORK BOUNDED DELAY MOBILITY NETWORK SET-UP TIME HIERARCHICAL NETWORK NETWORK DATA RATE

来源：评论

学校读者我要写书评

暂无评论

Technology Roadmap for Flexible Sensors

引用

ACS NANO 2023年第6期17卷 5211-5295页

作者： Luo, Yifei Abidian, Mohammad Reza Ahn, Jong-Hyun Akinwande, Deji Andrews, Anne M. Antonietti, Markus Bao, Zhenan Berggren, Magnus Berkey, Christopher A. Bettinger, Christopher John Chen, Jun Chen, Peng Cheng, Wenlong Cheng, Xu Choi, Seon-Jin Chortos, Alex Dagdeviren, Canan Dauskardt, Reinhold H. Di, Chong-an Dickey, Michael D. Duan, Xiangfeng Facchetti, Antonio Fan, Zhiyong Fang, Yin Feng, Jianyou Feng, Xue Gao, Huajian Gao, Wei Gong, Xiwen Guo, Chuan Fei Guo, Xiaojun Hartel, Martin C. He, Zihan Ho, John S. Hu, Youfan Huang, Qiyao Huang, Yu Huo, Fengwei Hussain, Muhammad M. Javey, Ali Jeong, Unyong Jiang, Chen Jiang, Xingyu Kang, Jiheong Karnaushenko, Daniil Khademhosseini, Ali Kim, Dae-Hyeong Kim, Il-Doo Kireev, Dmitry Kong, Lingxuan Lee, Chengkuo Lee, Nae-Eung Lee, Pooi See Lee, Tae-Woo Li, Fengyu Li, Jinxing Liang, Cuiyuan Lim, Chwee Teck Lin, Yuanjing Lipomi, Darren J. Liu, Jia Liu, Kai Liu, Nan Liu, Ren Liu, Yuxin Liu, Yuxuan Liu, Zhiyuan Liu, Zhuangjian Loh, Xian Jun Lu, Nanshu Lv, Zhisheng Magdassi, Shlomo Malliaras, George G. Matsuhisa, Naoji Nathan, Arokia Niu, Simiao Pan, Jieming Pang, Changhyun Pei, Qibing Peng, Huisheng Qi, Dianpeng Ren, Huaying Rogers, John A. Rowe, Aaron Schmidt, Oliver G. Sekitani, Tsuyoshi Seo, Dae-Gyo Shen, Guozhen Sheng, Xing Shi, Qiongfeng Someya, Takao Song, Yanlin Stavrinidou, Eleni Su, Meng Sun, Xuemei Takei, Kuniharu Tao, Xiao-Ming Tee, Benjamin C. K. Thean, Aaron Voon-Yew Trung, Tran Quang Wan, Changjin Wang, Huiliang Wang, Joseph Wang, Ming Wang, Sihong Wang, Ting Wang, Zhong Lin Weiss, Paul S. Wen, Hanqi Xu, Sheng Xu, Tailin Yan, Hongping Yan, Xuzhou Yang, Hui Yang, Le Yang, Shuaijian Yin, Lan Yu, Cunjiang Yu, Guihua Yu, Jing Yu, Shu-Hong Yu, Xinge Zamburg, Evgeny Zhang, Haixia Zhang, Xiangyu Zhang, Xiaosheng Zhang, Xueji Zhang, Yihui Zhang, Yu Zhao, Siyuan Zhao, Xuanhe Zheng, Yuanjin Zheng, Yu-Qing Zheng, Zijian Zhou, Tao Zhu, Bowen Zhu, Ming Zhu, Rong Zhu, Yangzhi Zhu, Yong Zou, Guijin Chen, Xiaodong 08-03 Innovis Singapore 138634 Republic of Singapore Innovative Centre for Flexible Devices (iFLEX) School of Materials Science and Engineering Nanyang Technological University Singapore 639798 Singapore Department of Biomedical Engineering University of Houston Houston Texas 77024 United States School of Electrical and Electronic Engineering Yonsei University Seoul 03722 Republic of Korea Department of Electrical and Computer Engineering The University of Texas at Austin Austin Texas 78712 United States Microelectronics Research Center The University of Texas at Austin Austin Texas 78758 United States Department of Chemistry and Biochemistry California NanoSystems Institute and Department of Psychiatry and Biobehavioral Sciences Semel Institute for Neuroscience and Human Behavior and Hatos Center for Neuropharmacology University of California Los Angeles Los Angeles California 90095 United States Colloid Chemistry Department Max Planck Institute of Colloids and Interfaces 14476 Potsdam Germany Department of Chemical Engineering Stanford University Stanford California 94305 United States Laboratory of Organic Electronics Department of Science and Technology Campus Norrköping Linköping University 83 Linköping Sweden Wallenberg Initiative Materials Science for Sustainability (WISE) and Wallenberg Wood Science Center (WWSC) SE-100 44 Stockholm Sweden Department of Materials Science and Engineering Stanford University Stanford California 94301 United States Department of Biomedical Engineering and Department of Materials Science and Engineering Carnegie Mellon University Pittsburgh Pennsylvania 15213 United States Department of Bioengineering University of California Los Angeles Los Angeles California 90095 United States School of Chemistry Chemical Engineering and Biotechnology Nanyang Technological University Singapore 637457 Singapore Nanobionics Group Department of Chemical and Biological Engineering Monash University Clayton Australia 3800 Monash

Humans rely increasingly on sensors to address grand challenges and to improve quality of life in the era of digitalization and big data. For ubiquitous sensing, flexible sensors are developed to overcome the limitations of conventional rigid counterparts. Despite rapid advancement in bench-side research over the last decade, the market adoption of flexible sensors remains limited. To ease and to expedite their deployment, here, we identify bottlenecks hindering the maturation of flexible sensors and propose promising solutions. We first analyze continued...challenges in achieving satisfactory sensing performance for real-world applications and then summarize issues in compatible sensor-biology interfaces, followed by brief discussions on powering and connecting sensor networks. Issues en route to commercialization and for sustainable growth of the sector are also analyzed, highlighting environmental concerns and emphasizing nontechnical issues such as business, regulatory, and ethical considerations. Additionally, we look at future intelligent flexible sensors. In proposing a comprehensive roadmap, we hope to steer research efforts towards common goals and to guide coordinated development strategies from disparate communities. Through such collaborative

关键词： soft materials mechanics engineering flexible electronics conformable sensors bioelectronics human-machine interfaces body area sensor networks technology translation sustainable electronics

来源：评论

学校读者我要写书评

暂无评论

Precision Rehabilitation for Patients Post-Stroke based on Electronic Health Records and Machine Learning

arXiv

引用

arXiv 2024年

作者： Gao, Fengyi Zhang, Xingyu Sivarajkumar, Sonish Denny, Parker E. Aldhahwani, Bayan M. Visweswaran, Shyam Shi, Ryan Hogan, William Bove, Allyn Wang, Yanshan Department of Health Information Management University of Pittsburgh PittsburghPA United States Department of Communication Science and Disorders University of Pittsburgh PittsburghPA United States Intelligent Systems Program School of Computing and Information University of Pittsburgh PittsburghPA United States Department of Physical Therapy University of Pittsburgh PittsburghPA United States Department of Medical Rehabilitation Sciences Umm Al-Qura University Makkah Saudi Arabia Department of Biomedical Informatics University of Pittsburgh PittsburghPA United States Department of Computer Science University of Pittsburgh Medical Center PittsburghPA United States Data Science Institute Medical College of Wisconsin MilwaukeeWI United States Hillman Cancer Center University of Pittsburgh Medical Center PittsburghPA United States

Objective In this study, we utilized statistical analysis and machine learning methods to examine whether rehabilitation exercises can improve patients post-stroke functional abilities, as well as forecast the improvement in functional abilities. Our dataset is patients’ rehabilitation exercises and demographic information recorded in the unstructured electronic health records (EHRs) data and free-text rehabilitation procedure notes. Through this study, our ultimate goal is to pinpoint the specific rehabilitation exercises that can effectively aid post-stroke patients in improving their functional outcomes in basic mobility (BM) and applied cognitive (AC) domains. Data sources We collected data for 265 stroke patients from the University of Pittsburgh Medical Center, accessed through the Rehabilitation Datamart With Informatics iNfrastructure for Research (ReDWINE). Methods We employed a pre-existing natural language processing (NLP) algorithm to extract data on rehabilitation exercises and developed a rule-based NLP algorithm to extract Activity Measure for Post-Acute Care (AM-PAC) scores, covering basic mobility (BM) and applied cognitive (AC) domains, from procedure notes. AM-PAC scores were collected at the initial rehabilitation visit and followed up at one and two months—key recovery periods. Changes in AM-PAC scores were classified based on the minimal clinically important difference (MCID), and significance was assessed using Friedman and Wilcoxon tests. To identify impactful exercises, we used Chi-square tests, Fisher's exact tests, and logistic regression for odds ratios. Additionally, we developed five machine learning models—logistic regression (LR), Adaboost (ADB), support vector machine (SVM), gradient boosting (GB), and random forest (RF)—to predict outcomes in functional ability. Results Statistical analyses revealed significant associations between functional improvements and specific exercises. In the AC domain, the BALANCE exercise showed substant

关键词： Statistical tests

来源：评论

学校读者我要写书评

暂无评论

Preface

引用

CEUR Workshop Proceedings 2009年 467卷

作者： Cena, Federica Farzan, Rosta Lops, Pasquale Department of Computer Science University of Turin Corso Svizzera 185 10149 Torino Italy Intelligent Systems Program University of Pittsburgh 5108 Sennott Square Building 210 S. Bouquet St. Pittsburgh United States Department of Computer Science University of Bari Via E. Orabona 4 70126 Bari Italy

来源：评论

学校读者我要写书评

暂无评论

ROLE OF SIMULATION IN RAPID PROTOTYPING FOR CONCEPT DEVELOPMENT

引用

NAVAL ENGINEERS JOURNAL 1991年第3期103卷 204-211页

作者： KING, JF BARTON, DE J. Fred King:is the manager of the Advanced Technology Department for Unisys in Reston Virginia. He earned his Ph.D. in mathematics from the University of Houston in 1977. He has been principal investigator of research projects in knowledge engineering pattern recognition and heuristic problem-solving. Efforts include the development of a multi-temporal multispectral classifier for identifying graincrops using LANDSAT satellite imagery data for NASA. Also as a member of the research team for a NCI study with Baylor College of Medicine and NASA he helped develop techniques for detection of carcinoma using multispectral microphotometer scans of lung tissue. He established and became technical director of the AI Laboratory for Ford Aerospace where he developed expert scheduling modeling and knowledge acquisition systems for NASA. Since joining Unisys in 1985 he has led the development of object-oriented programming environments blackboard architectures data fusion techniques using neural networks and intelligent data base systems. Douglas E. Barton:is manager of Logistics Information Systems for Unisys in Reston Virginia. He earned his B.A. degree in computer science from the College of William and Mary in 1978 and did postgraduate work in London as a Drapers Company scholar. Since joining Unisys in 1981 his work has concentrated on program management and software engineering of large scale data base management systems and design and implementation of knowledge-based systems in planning and logistics. As chairman of the Logistics Data Subcommittee of the National Security Industrial Association (NSIA) he led an industry initiative which examined concepts in knowledge-based systems in military logistics. His responsibilities also include evaluation development and tailoring of software engineering standards and procedures for data base and knowledge-based systems. He is currently program manager of the Navigation Information Management System which provides support to the Fleet Ballistic Missile Progr

A valuable technique during concept development is rapid prototyping of software for key design components. This approach is particularly useful when the optimum design approach is not readily apparent or several known alternatives need to be rapidly evaluated. A problem inherent in rapid prototyping is the lack of a "target system" with which to interface. Some alternatives are to develop test driver libraries, integrate the prototype with an existing working simulator, or build one for the specific problem. This paper presents a unique approach to concept development using rapid prototyping for concept development and scenario-based simulation for concept verification. The rapid prototyping environment, derived from artificial intelligence technology, is based on a blackboard architecture. The rapid prototype simulation capability is provided through an object-oriented modeling environment. It is shown how both simulation and blackboard technologies are used collectively to rapidly gain insight into a tenacious problem. A specific example will be discussed where this approach was used to evolve the logic of a mission controller for an autonomous underwater vehicle.

关键词： Military Engineering

来源：评论

学校读者我要写书评

暂无评论

Accurately predicting anticancer peptide using an ensemble of heterogeneously trained classifiers

引用

Informatics in Medicine Unlocked 2023年 42卷

作者： Azim, Sayed Mehedi Sabab, Noor Hossain Nuri Noshadi, Iman Alinejad-Rokny, Hamid Sharma, Alok Shatabda, Swakkhar Dehzangi, Iman Center for Computational and Integrative Biology Rutgers University Camden 08102 NJ United States Department of Computer Science and Engineering United International University Plot 2 United City Madani Avenue BaddaDhaka 1212 Bangladesh Department of Bioengineering University of California Riverside 92507 CA United States BioMedical Machine Learning Lab The Graduate School of Biomedical Engineering The University of New South Wales (UNSW Sydney) Sydney NSW 2052 Australia UNSW Data Science Hub UNSW Sydney Sydney NSW 2052 Australia Health Data Analytics Program AI-enabled Processes Research Centre Macquarie University Sydney 2109 Australia Institute for Integrated and Intelligent Systems Griffith University Brisbane Australia Laboratory for Medical Science Mathematics RIKEN Center for Integrative Medical Sciences Yokohama 230-0045 Japan Department of Computer Science Rutgers University Camden 08102 NJ United States

The use of therapeutic peptides for the treatment of cancer has received tremendous attention in recent years. Anticancer peptides (ACPs) are considered new anticancer drugs which have several advantages over chemistry-based drugs including high specificity, strong tumor penetration capacity, and low toxicity level for normal cells. Due to the rise of experimentally verified bioactive peptides, several in silico approaches became imperative for the investigation of the characteristics of ACPs. In this paper, we proposed a new machine learning tool named iACP-RF that uses a combination of several sequence-based features and an ensemble of three heterogeneously trained Random Forest classifiers to accurately predict anticancer peptides. Experimental results show that our proposed model achieves an accuracy of 75.9% which outperforms other state-of-the-art methods by a significant margin. We also achieve 0.52, 75.6%, and 76.2% in terms of Matthews Correlation Coefficient (MCC), Sensitivity, and Specificity, respectively. iACP-RF as a standalone tool and its source code are publicly available at: https://***/MLBC-lab/iACP-RF. © 2023 The Authors

关键词： Anticancer peptides Ensemble learning Feature extraction Heterogeneous classifiers Machine learning Random Forest

来源：评论

学校读者我要写书评

暂无评论

SRBench++: Principled Benchmarking of Symbolic Regression With Domain-Expert Interpretation

引用

IEEE Transactions on Evolutionary Computation 2024年 1-1页

作者： de Franca, F.O. Virgolin, M. Kommenda, M. Majumder, M.S. Cranmer, M. Espada, G. Ingelse, L. Fonseca, A. Landajuela, M. Petersen, B. Glatt, R. Mundhenk, N. Lee, C.S. Hochhalter, J.D. Randall, D.L. Kamienny, P. Zhang, H. Dick, G. Simon, A. Burlacu, B. Kasak, Jaan Machado, Meera Wilstrup, Casper Cavaz, W.G.L. Federal University of ABC Santo Andre Brazil Evolutionary Intelligence group Centrum Wiskunde and Informatica Science Park Amsterdam Netherlands University of Applied Sciences Upper Austria Hagenberg Austria Computational Health Informatics Program Boston Children’s Hospital Harvard Medical School Boston USA Center for Computational Astrophysics Flatiron Institute and Department of Astrophysical Sciences of Princeton University USA LASIGE Faculdade de Ciências Universidade de Lisboa Lisboa Portugal Computational Engineering Division Lawrence Livermore National Laboratory Livermore USA Department of Mechanical Engineering University of Utah Utah USA Meta FAIR France Victoria University of Wellington School of Engineering and Computer Science New Zealand University of otago Department of Information Science New Zealand Institut für Angewandte Physik Universität TübingenMax Planck Institute for Intelligent Systems Tübingen Germany Abzu AI Orient Plads 1 Nordhavn Denmark

Symbolic regression searches for analytic expressions that accurately describe studied phenomena. The main promise of this approach is that it may return an interpretable model that can be insightful to users, while maintaining high accuracy. The current standard for benchmarking these algorithms is SRBench, which evaluates methods on hundreds of datasets that are a mix of real-world and simulated processes spanning multiple domains. At present, the ability of SRBench to evaluate interpretability is limited to measuring the size of expressions on real-world data, and the exactness of model forms on synthetic data. In practice, model size is only one of many factors used by subject experts to determine how interpretable a model truly is. Furthermore, SRBench does not characterize algorithm performance on specific, challenging sub-tasks of regression such as feature selection and evasion of local minima. In this work, we propose and evaluate an approach to benchmarking SR algorithms that addresses these limitations of SRBench by 1) incorporating expert evaluations of interpretability on a domain-specific task, and 2) evaluating algorithms over distinct properties of data science tasks. We evaluate 12 modern symbolic regression algorithms on these benchmarks and present an in-depth analysis of the results, discuss current challenges of symbolic regression algorithms and highlight possible improvements for the benchmark itself. Authors

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：