检索结果-内蒙古大学图书馆

19th National Conference on Artificial Intelligence

作者： Guestrin, Carlos Hauskrecht, Milos Kveton, Branislav Berkeley Research Center Intel Corporation Department of Computer Science University of Pittsburgh Intelligent Systems Program University of Pittsburgh

Although many real-world stochastic planning problems are more naturally formulated by hybrid models with both discrete and continuous variables, current state-of-the-art methods cannot adequately address these problems. We present the first framework that can exploit problem structure for modeling and solving hybrid problems efficiently. We formulate these problems as hybrid Markov decision processes (MDPs with continuous and discrete state and action variables), which we assume can be represented in a factored way using a hybrid dynamic Bayesian network (hybrid DBN). We present a new linear program approximation method that exploits the structure of the hybrid MDP and lets us compute approximate value functions more efficiently. In particular, we describe a new factored discretization of continuous variables that avoids the exponential blow-up of traditional approaches. We provide theoretical bounds on the quality of such an approximation and on its scale-up potential. We support our theoretical arguments with experiments on a set of control problems with up to 28-dimensional continuous state space and 22-dimensional action space. Copyright © 2004, American Association for Artificial Intelligence. All rights reserved.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

Dynamic Sampling-Based Meta-Learning Using Multilingual Acoustic Data for Under-Resourced Speech Recognition

引用

IEEE Access 2024年 12卷 106070-106083页

作者： Hsieh, I-Ting Wu, Chung-Hsien Zhao, Zhe-Hong National Cheng Kung University Graduate Program of Multimedia Systems and Intelligent Computing Tainan70101 Taiwan National Cheng Kung University Department of Computer Science and Information Engineering Tainan70101 Taiwan

Under-resourced automatic speech recognition (ASR) has become an active field of research and has experienced significant progress during the past decade. However, the performance of under-resourced ASR trained by existing methods is still far inferior to high-resourced ASR for practical applications. In this paper, speech data from languages that share the most phonemes with the under-resourced language are selected as supplementary resources for meta-training based on the Model-Agnostic Meta-Learning (MAML) strategy. Besides supplementary language selection, this paper proposes a dynamic sampling method instead of the original random sampling method to select support and query sets for each task in MAML to improve meta-training performance. In this study, Taiwanese is selected as the under-resourced language, and the speech corpus of five languages, including Mandarin, English, Japanese, Cantonese, and Thai, are chosen as supplementary training data for acoustic model training. The proposed dynamic sampling approach uses phonemes, pronunciation, and speech recognition models as the basis to determine the proportion of each supplementary language to select helpful utterances for MAML. For evaluation, with the selected utterances from each supplementary language for meta-training, we obtained a Word Error Rate of 20.24% and a Syllable Error Rate of 8.35% for Taiwanese ASR, which were better than the baseline model (26.18% and 13.99%) using only the Taiwanese corpus and other methods. © 2013 IEEE.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Evaluating an intelligent tutoring system for making legal arguments with hypotheticals

引用

International Journal of Artificial Intelligence in Education 2009年第4期19卷 401-424页

作者： Pinkwart, Niels Ashley, Kevin Lynch, Collin Aleven, Vincent Department of Informatics Clausthal University of Technology Clausthal-Zellerfeld Germany Learning Research and Development Center School of Law and Intelligent Systems Program University of Pittsburgh Pittsburgh PA United States Learning Research and Development Center Intelligent Systems Program University of Pittsburgh Pittsburgh PA United States Human-Computer Interaction Institute School of Computer Science Carnegie Mellon University Pittsburgh PA United States

Argumentation is a process that occurs often in ill-defined domains and that helps deal with the illdefinedness. Typically a notion of "correctness" for an argument in an ill-defined domain is impossible to define or verify formally because the underlying concepts are open-textured and the quality of the argument may be subject to discussion or even expert disagreement. Previous research has highlighted the advantages of graphical representations for learning argumentation skills. A number of intelligent tutoring systems have been built that support students in rendering arguments graphically, as they learn argumentation skills. The relative instructional benefits of graphical argument representations have not been reliably shown, however. In this paper we present a formative evaluation of LARGO (Legal ARgument Graph Observer), a system that enables law students graphically to represent examples of legal interpretation with hypotheticals they observe while reading texts of U.S. Supreme Court oral arguments. We hypothesized that, compared to a text-based alternative, LARGO's diagramming language geared toward depicting hypothetical reasoning processes, coupled with non-directive feedback, helps students better extract the important information from argument transcripts and better learn argumentation skills. A first pilot study, conducted with volunteer first-semester law students, provided support for the hypothesis. The system especially helped lower-aptitude students learn argumentation skills, and LARGO improved the reading skills of students as they studied expert arguments. A second study with LARGO was conducted as a mandatory part of a first-semester University law course. Although there were no differences in the learning outcomes of the two conditions, the second study showed some evidence that those students who engaged more with the argument diagrams through the advice did better than the text condition. One lesson learned from these two studies is that gr

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Learning to rank sentences for explaining statutory terms 4

Learning to rank sentences for explaining statutory terms

引用

4th Workshop on Automated Semantic Analysis of Information in Legal Text, ASAIL 2020

作者： Savelka, Jaromir Ashley, Kevin D. School of Computer Science Carnegie Mellon University United States School of Law Intelligent Systems Program University of Pittsburgh United States

We explore using classical feature engineering-based learning-to-rank approaches (LTR) to discover sentences for explaining the meaning of statutory terms. We compiled a list of 129 descriptive features that model retrieved sentences, their relationships to statutory terms, and their statutory provisions of origin. Using a statutory interpretation data set (26,959 sentences) we showed how the proposed feature set could be utilized in learning-to-rank settings with reasonable effectiveness. We showed that off-the-shelf machine learning algorithms perform significantly better than BM25 baselines (NDCG@100 of 0.77 vs 0.68). Copyright © 2020 for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Contingency Selection in Plan Generation

Contingency Selection in Plan Generation

引用

1996 AAAI Fall Symposium

作者： Onder, Nilufer Pollack, Martha E. Department of Computer Science University of Pittsburgh PittsburghPA15260 United States Department of Computer Science Intelligent Systems Program University of Pittsburgh PittsburghPA15260 United States

Akey question in conditional planning is: howmany, andwhich of the possible executionfailures shouldbe plannedfor? Onecannot, in general, plan for all the possible failures because the search spaceis too large. One cannotig noreall the possible failures, or onewill fail to produce sufficiently flexibleplans. In this paper, wedescribe an approachto conditional planning that attempts to identify the contingencies that contribute the mostto a plan's overall utility. Plan generation proceeds by handling the most important contingencies first, extending the plan to include actions that will be taken in case the contingency fails. Wediscuss the representational issues that mustbe addressedin order to implementsuch an algorithm, and present an examplewhichillustrates our approach. © 1996, AAAI (***). All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

intelligent Constellation Generation based on Autoencoder Communication System 2

Intelligent Constellation Generation based on Autoencoder Co...

引用

2nd IEEE International Conference on computer Vision and Machine Intelligence, CVMI 2023

作者： Matsumoto, Kaisei Toma, Takao Oshiro, Shiho Wada, Tomohisa Computer Science and Intelligent Systems Program University of the Ryukyus Okinawa Japan Magna Design Net Inc Okinawa Japan Information Technology Center University of the Ryukyus Okinawa Japan Area of Computer Science and Intelligent Systems University of the Ryukyus Dept. of Engineering Okinawa Japan

ISBN: (纸本)9798350305142

This paper discusses intelligent constellation generation based on autoencoder communication system. In previous studies, the amplitude was set to fluctuate between r=0.0 and 1.0. However, when checking the generated constellation, distortion was confirmed instead of the conventional symbol arrangement. Therefore, in this paper, it compares the case where the amplitude is constant, the case where the average amplitude within a Minibatch is 1, and the case where the average amplitude is 1 for Interval time. The communication standard used in this research is IEEE 802.11a, assuming wireless Local Area Network (LAN) specifications. The IEEE 802.11a standard has an Fast Fourier Transform (FFT) length of 64, a subcarrier number of 52, and Quadrature Phase Shift Keying (QPSK) and 16 Quadrature Amplitude Modulation (QAM), modulation methods. A guard interval of 800 ns is added and the symbol length is 4000 ns. First, a simulation was performed under the condition that the amplitude was kept constant. QPSK with 4 symbols, constant amplitude model is rounded more than previous research result. 16QAM with 16 symbols is arranged regularly like lined up on a line. Second, the simulation was performed under the condition that the average amplitude within the minibatch was set to 1. QPSK with 4 symbols, appears to rotate clockwise. 16QAM with 16 symbols has a more uniform symbol placement than previous research result. Third, a simulation was performed under the condition that the average amplitude within Interval time was set to 1. QPSK with 4 symbols, is the closest to square among QPSK output results so far. The direction is slightly tilted, but if it can be rotated a little more, it may be possible to reproduce the same symbol arrangement as before. 16QAM with 16 symbols, the symbol arrangement is biased as a whole. However, it can be seen that are arranged in line on the line, perhaps due to regularity. As future work, in addition to the conditions set this time, it will exa

关键词： Quadrature phase shift keying

来源：评论

学校读者我要写书评

暂无评论

Scalability in Autoencoder-based OFDM Communication System 2

Scalability in Autoencoder-based OFDM Communication System

引用

2nd IEEE International Conference on computer Vision and Machine Intelligence, CVMI 2023

作者： Tsugawa, Seizan Toma, Takao Oshiro, Shiho Wada, Tomohisa University of the Ryukyus Computer Science and Intelligent Systems Program Okinawa Japan Magna Design Net Inc Okinawa Japan University of the Ryukyus Information Technology Center Okinawa Japan University of the Ryukyus Area of Computer Science and Intelligent Systems Dept. of Engineering Okinawa Japan

ISBN: (纸本)9798350305142

This paper proposed Scalability in Autoencoder-based Orthogonal Frequency Division Multiplexing(OFDM) communication system. In the previous research, only the comparison between IEEE802.11a and Autoencoder by the conventional OFDM communication system was performed, and it was proved that the communication system created by Autoencoder exceeded the performance of the conventional system. Therefore, in this paper, it uses IEEE802.11n and compare whether it can be improved by expanding the bandwidth and using ***802.11n standard has an FFT length of 128, a subcarrier number of 114 (108 for data), and modulation schemes of Quadrature Phase Shift Keying(QPSK), 16 Quadrature Amplitude Modulation (16QAM). The GI length is 800ns and the symbol length is 4000ns. In the simulation, a computer simulation was performed using a conventional OFDM communication system and a communication system generated by Autoencoder. Assuming that the simulation environment had an Signal-to-Noise Ratio (SNR) of 0 to 30 and an amplitude r of 0.0 to 1.0, the Symbol Error Rate (SER) status for each SNR was output. As a result of computer simulation, QPSK converged at SNR 27 at IEEE 802.11a, but was able to reduce SER overwhelmingly to SNR 12 at IEEE 802.11n. Also, in 16QAM the convergence at r=0.0 is the same as for SNR22 , but in IEEE 802.11a it does not converge after r=0.6, but in IEEE 802.11n it does not converge only at r=0.9 and r=1.0. As a future task, it will use IEEE802.11ac, which enables communication speeds several times faster than IEEE802.11n, examine whether it is possible to further improve accuracy. And it will continue our research to correspond MIMO communication. © 2023 IEEE.

关键词： Orthogonal frequency division multiplexing

来源：评论

学校读者我要写书评

暂无评论

LEATHER: A Framework for Learning to Generate Human-like Text in Dialogue 2

LEATHER: A Framework for Learning to Generate Human-like Tex...

引用

2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing, AACL-IJCNLP 2022

作者： Sicilia, Anthony Alikhani, Malihe Intelligent Systems Program University of Pittsburgh PittsburghPA United States Computer Science Department University of Pittsburgh PittsburghPA United States

ISBN: (纸本)9781959429043

Algorithms for text-generation in dialogue canbe misguided. For example, in task-orientedsettings, reinforcement learning that optimizesonly task-success can lead to abysmal lexical diversity. We hypothesize this is due to poor theoretical understanding of the objectives in textgeneration and their relation to the learning process (i.e., model training). To this end, we propose a new theoretical framework for learningto generate text in dialogue. Compared to existing theories of learning, our framework allowsfor analysis of the multi-faceted goals inherent to text-generation. We use our frameworkto develop theoretical guarantees for learnersthat adapt to unseen data. As an example, weapply our theory to study data-shift within a cooperative learning algorithm proposed for theGuessWhat?! visual dialogue game. From thisinsight, we propose a new algorithm, and empirically, we demonstrate our proposal improvesboth task-success and human-likeness of thegenerated text. Finally, we show statistics fromour theory are empirically predictive of multiple qualities of the generated dialogue, suggesting our theory is useful for model-selectionwhen human evaluations are not available. © AACL-IJCNLP *** rights reserved

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Keyword annotation of biomedicai documents with graph-based similarity methods 2012

Keyword annotation of biomedicai documents with graph-based ...

引用

2012 IEEE International Conference on Bioinformatics and Biomedicine, BIBM2012

作者： Wang, Shuguang Hauskrecht, Milos Intelligent Systems Program University of Pittsburgh Pittsburgh PA United States Department of Computer Science University of Pittsburgh Pittsburgh PA United States

ISBN: (纸本)9781467325585

In this paper, we present a new approach that lets us extract, and represent relations among terms (concepts) in the documents and uses these relations to support various document analysis applications. Our approach works by building a graph of local co-occurrence relations among terms that are extracted directly from text and by defining a global similarity metric among these terms and sets of terms using the graph and its connectivity. We demonstrate the benefit of the approach on the problem of MeSH keyword annotation of documents based on their abstracts. © 2012 IEEE.

关键词： Graphic methods

来源：评论

学校读者我要写书评

暂无评论

Artificial intelligence for modelling infectious disease epidemics

引用

Nature 2025年第8051期638卷 623-635页

作者： Kraemer, Moritz U. G. Tsui, Joseph L.-H. Chang, Serina Y. Lytras, Spyros Khurana, Mark P. Vanderslott, Samantha Bajaj, Sumali Scheidwasser, Neil Curran-Sebastian, Jacob Liam Semenova, Elizaveta Zhang, Mengyan Unwin, H. Juliette T. Watson, Oliver J. Mills, Cathal Dasgupta, Abhishek Ferretti, Luca Scarpino, Samuel V. Koua, Etien Morgan, Oliver Tegally, Houriiyah Paquet, Ulrich Moutsianas, Loukas Fraser, Christophe Ferguson, Neil M. Topol, Eric J. Duchêne, David A. Stadler, Tanja Kingori, Patricia Parker, Michael J. Dominici, Francesca Shadbolt, Nigel Suchard, Marc A. Ratmann, Oliver Flaxman, Seth Holmes, Edward C. Gomez-Rodriguez, Manuel Schölkopf, Bernhard Donnelly, Christl A. Pybus, Oliver G. Cauchemez, Simon Bhatt, Samir Pandemic Sciences Institute University of Oxford Oxford United Kingdom Department of Biology University of Oxford Oxford United Kingdom Department of Electrical Engineering and Computer Science University of California Berkeley Berkeley CA United States UCSF UC Berkeley Joint Program in Computational Precision Health Berkeley CA United States Division of Systems Virology Department of Microbiology and Immunology The Institute of Medical Science The University of Tokyo Tokyo Japan Section of Epidemiology Department of Public Health University of Copenhagen Copenhagen Denmark Oxford Vaccine Group University of Oxford and NIHR Oxford Biomedical Research Centre Oxford United Kingdom Department of Epidemiology and Biostatistics Imperial College London London United Kingdom Department of Computer Science University of Oxford Oxford United Kingdom School of Mathematics University of Bristol Bristol United Kingdom MRC Centre for Global Infectious Disease Analysis School of Public Health Imperial College London London United Kingdom Department of Statistics University of Oxford Oxford United Kingdom Doctoral Training Centre University of Oxford Oxford United Kingdom Institute for Experiential AI Northeastern University MA Boston Thailand Santa Fe Institute Santa Fe NM United States World Health Organization Regional Office for Africa Brazzaville Congo WHO Hub for Pandemic and Epidemic Intelligence Health Emergencies Programme World Health Organization Berlin Germany Centre for Epidemic Response and Innovation (CERI) School for Data Science and Computational Thinking Stellenbosch University Stellenbosch South Africa African Institute for Mathematical Sciences (AIMS) South Africa Muizenberg Cape Town South Africa Genomics England London United Kingdom Scripps Research La Jolla CA United States Department of Biosystems Science and Engineering ETH Zürich Basel Switzerland Swiss Institute of Bioinformatics Lausanne Switzerland The Ethox Centre Nuffield

Infectious disease threats to individual and public health are numerous, varied and frequently unexpected. Artificial intelligence (AI) and related technologies, which are already supporting human decision making in economics, medicine and social science, have the potential to transform the scope and power of infectious disease epidemiology. Here we consider the application to infectious disease modelling of AI systems that combine machine learning, computational statistics, information retrieval and data science. We first outline how recent advances in AI can accelerate breakthroughs in answering key epidemiological questions and we discuss specific AI methods that can be applied to routinely collected infectious disease surveillance data. Second, we elaborate on the social context of AI for infectious disease epidemiology, including issues such as explainability, safety, accountability and ethics. Finally, we summarize some limitations of AI applications in this field and provide recommendations for how infectious disease epidemiology can harness most effectively current and future developments in AI. © Springer Nature Limited 2025.

关键词：

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：