检索结果-内蒙古大学图书馆

MACHINE LEARNING 2017年第12期106卷 1905-1932页

作者： Nitti, Davide Belle, Vaishak De Laet, Tinne De Raedt, Luc Katholieke Univ Leuven Dept Comp Sci B-3001 Leuven Belgium Univ Edinburgh Sch Informat Edinburgh EH8 9AB Midlothian Scotland Katholieke Univ Leuven Fac Engn Sci B-3001 Leuven Belgium

We study planning in relational Markov decision processes involving discrete and continuous states and actions, and an unknown number of objects. this combination of hybrid relational domains has so far not received a lot of attention. While both relational and hybrid approaches have been studied separately, planning in such domains is still challenging and often requires restrictive assumptions and approximations. We propose HYPE: a sample-based planner for hybrid relational domains that combines model-based approaches with state abstraction. HYPE samples episodes and uses the previous episodes as well as the model to approximate the Q-function. In addition, abstraction is performed for each sampled episode, this removes the complexity of symbolic approaches for hybrid relational domains. In our empirical evaluations, we show that HYPE is a general and widely applicable planner in domains ranging from strictly discrete to strictly continuous to hybrid ones, handles intricacies such as unknown objects and relational models. Moreover, empirical results showed that abstraction provides significant improvements.

关键词： MDP Probabilistic planning logic programming Relational MDP Hybrid Hybrid relational MDP Probabilistic programming Abstraction logical regression Importance sampling

来源：评论

学校读者我要写书评

暂无评论

Estimation-based search space traversal in Pilp environments 1

引用

26th international conference on inductive logic programming, ilp 2016

作者： Côrte-Real, Joana Dutra, Inês Rocha, Ricardo Faculty of Sciences CRACS INESC TEC University of Porto Rua do Campo Alegre 1021/1055 Porto4169-007 Portugal

ISBN: (数字)9783319633428

ISBN: (纸本)9783319633411

Probabilistic inductive logic programming (Pilp) systems extend ilp by allowing the world to be represented using probabilistic facts and rules, and by learning probabilistic theories that can be used to make predictions. However, such systems can be inefficient both due to the large search space inherited from the ilp algorithm and to the probabilistic evaluation needed whenever a new candidate theory is generated. To address the latter issue, this work introduces probability estimators aimed at improving the efficiency of Pilp systems. An estimator can avoid the computational cost of probabilistic theory evaluation by providing an estimate of the value of the combination of two subtheories. Experiments are performed on three real-world datasets of different areas (biology, medical and web-based) and show that, by reducing the number of theories to be evaluated, the estimators can significantly shorten the execution time without losing probabilistic accuracy. © Springer international Publishing AG 2017.

关键词： inductive logic programming (ilp)

来源：评论

学校读者我要写书评

暂无评论

Extracting rules for successful conditions for artificial insemination in dairy cattle using inductive logic programming 2017

Extracting rules for successful conditions for artificial in...

引用

9th international conference on Machine Learning and Computing, ICMLC 2017

作者： Matsumoto, Atsushi Kubota, Chikara Ohwada, Hayato Department of Industrial Administration Faculty of Science and Technology Tokyo University of Science 2641 Yamazaki Noda Chiba278-8510 Japan Joint Faculty of Veterinary Medicine Laboratory of Theriogenology Kagoshima University 1-24-24 Korimoto Kagoshima Kagoshima890-0065 Japan

ISBN: (纸本)9781450348171

this paper describes a method of pattern extraction to identify successful conditions for artificial insemination in dairy cattle using inductive logic programming. the fertility of lactating dairy cows is economically important but the mean reproductive performance of Holstein cows has declined during the past three decades. the Milk production increases after birth and gradually decreases after several weeks, but it increases again upon the next birth. Increasing the probability of successful artificial insemination is thus economically important. However the success rate of artificial insemination is 20 to 30 %. the amount of progesterone is closely related to the estrus cycle, and can be measured from raw milk. In this study, we extracted variation pattern from time-series data related to dairy cattle including the amount of progesterone using ilp. the success pattern or failure patterns for artificial insemination extracted by the ilp system can be used for decision making on artificial insemination. © 2017 ACM.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Discovering Rules of Subtle Deficits Indicating Mild Cognitive Impairment Using inductive logic programming

Discovering Rules of Subtle Deficits Indicating Mild Cogniti...

引用

19th international conference on Human-Computer Interaction (HCI international)

作者： Abe, Keisuke Martono, Niken Prasasti Yamaguchi, Takehiko Ohwada, Hayato Giovannetti, Tania Tokyo Univ Sci Dept Ind Adm Katsushika Japan Tokyo Univ Sci Dept Appl Elect Katsushika Japan Temple Univ Dept Psychol Philadelphia PA 19122 USA

ISBN: (纸本)9783319585246;9783319585239

Recently, Japan has been experiencing a declining birthrate and an increasingly aging population;as a result, the number of dementia patients is increasing. Current medical science has no way to treat dementia completely after onset. therefore, it is necessary to detect mild cognitive impairment (MCI) in the early stage just before dementia develops. It is clear that MCI patients who exhibit subtle deficits in daily living behavior (in this study, micro-errors (MEs)) have declining cognitive function associated with cognitive impairment. Virtual reality (VR) technology has been actively utilized in rehabilitation and therapy, and here we use an application known as Virtual Kitchen (VK). In this work, we analyze how ME happens. We use finger movement data and subtask information from VK. Our methodology proposes a combination of inductive logic programming (ilp) and the sliding window algorithm. Because ilp can extract expressive rules but is susceptible to noise and memory hog, it is difficult to use sensor data directly for learning. Sliding window is used as its ability to reduce the amount of data while holding the shape of original time series data. From preliminary experiments, we obtained some rules of ME occurrence that are related to differences in speed, time interval, and subtask. We obtained results that explain how ME occurrence is generally related to subtask and finger speed. In the future, we will use more positive samples and conduct more experiments to obtain better and more accurate results.

关键词： Cognitive impairment Virtual reality Time series Data mining

来源：评论

学校读者我要写书评

暂无评论

inductive logic programming meets relational databases: Efficient learning of markov logic networks 1

引用

26th international conference on inductive logic programming, ilp 2016

作者： Malec, Marcin Khot, Tushar Nagy, James Blask, Erik Natarajan, Sriraam Indiana University Bloomington BloomingtonIN United States Allen Institute of AI Seattle United States Air Force Research Laboratory Riverside United States

ISBN: (数字)9783319633428

ISBN: (纸本)9783319633411

Statistical Relational Learning (SRL) approaches have been developed to learn in presence of noisy relational data by combining probability theory with first order logic. While powerful, most learning approaches for these models do not scale well to large datasets. While advances have been made on using relational databases with SRL models [14], they have not been extended to handle the complex model learning (structure learning task). We present a scalable structure learning approach that combines the benefits of relational databases with search strategies that employ rich inductive bias from inductive logic programming. We empirically show the benefits of our approach on boosted structure learning for Markov logic Networks. © Springer international Publishing AG 2017.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

Generating Rules of Action Transition in Errors in Daily Activities from a Virtual Reality-Based Training Data

Generating Rules of Action Transition in Errors in Daily Act...

引用

19th international conference on Human-Computer Interaction (HCI international)

作者： Martono, Niken Prasasti Abe, Keisuke Yamaguchi, Takehiko Ohwada, Hayato Giovannetti, Tania Tokyo Univ Sci Dept Ind Adm Noda Chiba Japan Tokyo Univ Sci Dept Appl Elect Tokyo Japan Temple Univ Dept Psychol Philadelphia PA 19122 USA

ISBN: (纸本)9783319585246;9783319585239

Developments in virtual reality (VR) have advanced numerous applications in clinical settings in the areas of learning and treatment in neuropsychology. Emerging VR applications today focus on the challenge of diagnosis and cognitive training of mild cognitive impairment (MCI) and dementia patients and address navigation and orientation, face recognition, cognitive functionality, and other instrumental activities of daily living (IADL). the information recorded and captured by VR-based technology is real-time and can be advantageous for further analysis of patients' characteristics. the present study sought to utilize the data collected from VR-based software and a leap-motion device for learning in MCI cases to generate the rules for errors and action slips based on finger-action transitions when performing IADL. the finger motion was recorded as a time-series database, then an induction technique called inductive logic programming (ilp), which uses logical and clausal language to represent the training data, was used to discover a concise classification rule using logical programming.

关键词： Virtual reality inductive logic programming Micro slips Micro errors Mild cognitive impairment

来源：评论

学校读者我要写书评

暂无评论

Early diagnosis of mild cognitive impairment: A case study in approaches to inductive-logic programming 16

Early diagnosis of mild cognitive impairment: A case study i...

引用

16th IEEE international conference on Cognitive Informatics and Cognitive Computing, ICCI*CC 2017

作者： Martono, Niken Prasasti Yamaguchi, Takehiko Ohwada, Hayato Department of Industrial Administration Tokyo University of Science Japan Department of Applied Electronics Tokyo University of Science Japan School of Business and Management Bandung Institute of Technology Indonesia

ISBN: (纸本)9781538607701

Recent rapid advances in data collection routines in clinical science have led to a trend of storing patient data in a heterogeneous database. the lack of existing computing tools to enable operability to use machine learning on these heterogeneous data sources is a barrier to the healthcare sciences. Healthcare data is usually complex and highly context-dependent, and it requires modern computational tools to handle the complexity of such data. this study sought to utilize the data collected from virtual reality (VR)-based software and a leap-motion device used for learning in mild cognitive impairment (MCI) cases to enable early detection of MCI by analyzing the classification rules for errors (action slips) based on finger-action transitions when performing instrumental activities of daily living (IADL). Finger motion was recorded as a time-series database. An induction technique known as inductive-logic programming (ilp), which uses logical and clausal language to represent the training data, was then used to discover a concise classification rule using logical programming. We were able to generate rules on how action transitions of the finger in the experiments were related to the pattern of micro-errors that indicate the difference of error regarding the length of the no-motion state of the finger. © 2017 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Distributional learning of regular formal graph system of bounded degree 1

引用

26th international conference on inductive logic programming, ilp 2016

作者： Shoudai, Takayoshi Matsumoto, Satoshi Suzuki, Yusuke Faculty of International Studies Kyushu International University Kitakyushu Japan Faculty of Science Tokai University Hiratsuka Japan Graduate School of Information Sciences Hiroshima City University Hiroshima Japan

ISBN: (数字)9783319633428

ISBN: (纸本)9783319633411

In this paper, we describe how distributional learning techniques can be applied to formal graph system (FGS) languages. An FGS is a logic program that deals with term graphs instead of the terms of first-order predicate logic. We show that the regular FGS languages of bounded degree with the 1-finite context property (1-FCP) and bounded treewidth property can be learned from positive data and membership queries. © Springer international Publishing AG 2017.

关键词： Graph theory

来源：评论

学校读者我要写书评

暂无评论

Learning disjunctive logic programs from interpretation transition 26

Learning disjunctive logic programs from interpretation tran...

引用

26th international conference on inductive logic programming (Short Papers), ilp 2016

作者： Huang, Yi Wang, Yisong Zhang, Ying Zhang, Mingyi Guizhou University Guiyang550025 China Guizhou Academy of Sciences Guiyang550001 China Chongqing University of Arts and Sciences Chongqing402160 China

We present a new framework for learning disjunctive logic programs from interpretation transitions, called LFDT. It is a nontrivial extension to Inoue, Ribeiro and Sakama's LF1T learning framework, which learns normal logic programs from interpretation transitions. Two resolutions for disjunctive rules are also presented and used in LFDT to simplify learned disjunctive rules.

关键词： Computer circuits

来源：评论

学校读者我要写书评

暂无评论

2017 27th international conference on Field Programmable logic and Applications, FPL 2017

2017 27th International Conference on Field Programmable Log...

引用

27th international conference on Field Programmable logic and Applications, FPL 2017

ISBN: (纸本)9789090304281

the proceedings contain 109 papers. the topics discussed include: evaluating FPGA clusters under wide ranges of design parameters;a high-performance system-on-chip architecture for direct tracking for SLAM;Taiga: a new RISC-V soft-processor framework enabling high performance CPU architectural features;a generic high throughput architecture for stream processing;enabling partial reconfiguration and low latency routing using segmented FPGA NOCs;rapid implementation of a partially reconfigurable video system with PYNQ;a partial reconfiguration based microphone array network emulator;a dynamic partial reconfigurable overlay concept for PYNQ;ARMHEX: a hardware extension for DIFT on arm-based SOCs;voltage drop-based fault attacks on FPGAs using valid bitstreams;high throughput AES encryption/decryption with efficient reordering and merging techniques;comparison of hardware and software implementations of selected lightweight block ciphers;one size does not fit all: implementation trade-offs for iterative stencil computations on FPGAs;FPGA-based design of a self-checking TMR voter;accelerator-in-switch: a framework for tightly coupled switching hub and an accelerator with FPGA;stripe: signal selection for runtime power estimation;a programming model and runtime system for approximation-aware heterogeneous computing;Vivado design interface: an export/import capability for Vivado FPGA designs;optimizing streaming stencil time-step designs via FPGA floorplanning;and in-switch approximate processing: delayed tasks management for MapReduce applications.

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：