检索结果-内蒙古大学图书馆

IEEE Latin American Symposium on Circuits and Systems

作者： Daniel M. Mufioz Carlos H. Llanos Leandro dos S. Coelho Mauricio Ayala-Rincon Department of Mechanical Engineering Automation and Control Group/GRACO University of Brasilia Industrial and Systems Engineering Graduate Program LAS/PPGEPS Pontifical Catholic University of Parana Department of Computer Science and Mathematics University of Brasilia

ISBN: (纸本)9781467312073

Artificial bee colony (ABC) is an optimization algorithm inspired on the intelligent behavior of honey bee swarms. It is suitable to be applied when mathematical techniques are impractical or provide suboptimal solutions. As a population-based algorithm, the ABC suffers on large execution times specifically for embedded optimization problems with computational limitations. For that we propose a hardware parallel architecture of the opposition-based ABC algorithm (HPOABC) that facilitates the implementation in Field programmable Gate Arrays (FPGAs). Numerical simulations using four well-known benchmark problems demonstrate that the opposition-based approach allows the algorithm to improve its functionality, preserving the swarm diversity. Additionally, synthesis results point outs that the HPOABC architecture is effectively mapped in hardware and is suitable for embedded applications.

关键词： Global optimization Swarm intelligence Artificial bee colony FPGAs Floating-point arithmetic

来源：评论

学校读者我要写书评

暂无评论

Learning with which local decision expert to consult next case study: Arrhythmia diagnosis

Learning with which local decision expert to consult next ca...

引用

作者： Mirian, Maryam S. Ahmadabadi, Majid Nili Araabi, Babak N. Ajallooeian, Mohammad M. Control and Intelligent Processing Centre of Excellence Department of Electrical and Computer Engineering University of Tehran Iran School of Cognitive Science IPM Tehran Iran

The proposed approach is based on the classical model of *** its and tries to concurrently learn two tightly coupled issues. As the main goal it learns the optimal classification and at the same time, it learns the best sequence of council with previously designed local decision *** to reach the former optimal classification strategy. Local experts are in fact local classifiers who have learned the sub-optimal decision mnalcing based on just a portion of the whole feature space. The methodology is that in the first stage we generate different feature spaces by binning the features according to their potential relevance and then randomly selecting from the bins. At the second stage we train a classifier for each of the resulting feature subsets. Finally, we use a continuous Q-learning variant for learning a combiner for the predictions of these classifiers which is the key contribution of the paper. Actually the mneta-learner in the last stage learns to combine different global models, each induced from a different feature subset. The domain of medical diagnosis (specifically Arrhythmia recognition) by using UCI datasets is opted as the benchmark. The acquired classification rate certifies that the proposed approach is quite comnpamble with the results have been reported so far. Moreover this recognition is achieved by as few consultations as possible which is another key different merit for our approach. © 2011 ISSN.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

A constrained alternating least squares nonnegative matrix factorization algorithm enhances task-related neuronal activity detection from single subject's fMRI data

A constrained alternating least squares nonnegative matrix f...

引用

2011 International Conference on Machine Learning and Cybernetics, ICMLC 2011

作者： Ding, Xiaoyu Lee, Jong-Hwan Lee, Seong-Whan Department of Computer Science and Engineering Korea University Seoul 136-713 Korea Republic of Department of Brain and Cognitive Engineering Korea University Seoul 136-713 Korea Republic of

ISBN: (纸本)9781457703065

This paper proposes a constrained alternating least squares nonnegative matrix factorization algorithm (cALSNMF) to enhance alternating least squares non-negative matrix factorization (ALSNMF) in detecting task-related neuronal activity from single subject's fMRI data. In cALSNMF, a new cost function is defined in consideration of the uncorrelation and overdeter-mined problems of fMRI data, A novel training procedure is generated by combining optimal brain surgeon (OBS) algorithm in weight updating process, which considers the interaction among voxels. The experiments on both simulated data and fMRI data show that cALSNMF fits data better without any prior information and works more adaptively than original ALSNMF on detecting task-related neuronal activity. © 2011 IEEE.

关键词： Cost functions

来源：评论

学校读者我要写书评

暂无评论

Three theorems: Brain-like networks logically reason and optimally generalize

Three theorems: Brain-like networks logically reason and opt...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Juyang Weng Department of Computer Science and Engineering Cognitive Science Program and Neuroscience Program Michigan State University East Lansing MI USA

Finite Automata (FA) is a base net for many sophisticated probability-based systems of artificial intelligence. However, an FA processes symbols, instead of images that the brain senses and produces (e.g., sensory images and motor images). Of course, many recurrent artificial neural networks process images. However, their non-calibrated internal states prevent generalization, let alone the feasibility of immediate and error-free learning. I wish to report a general-purpose Developmental program (DP) for a new type of, brain-anatomy inspired, networks - Developmental Networks (DNs). The new theoretical results here are summarized by three theorems. (1) From any complex FA that demonstrates human knowledge through its sequence of the symbolic inputs-outputs, the DP incrementally develops a corresponding DN through the image codes of the symbolic inputs-outputs of the FA. The DN learning from the FA is incremental, immediate and error-free. (2) After learning the FA, if the DN freezes its learning but runs, it generalizes optimally for infinitely many image inputs and actions based on the embedded inner-product distance, state equivalence, and the principle of maximum likelihood. (3) After learning the FA, if the DN continues to learn and run, it “thinks” optimally in the sense of maximum likelihood based on its past experience.

关键词： Neurons Tin Automata Humans Brain models Learning systems

来源：评论

学校读者我要写书评

暂无评论

Microstructural and electrical properties of Ce_0.9Gd_0.1O1.95 thin film electrolyte in solid oxide fuel cells (vol 26, pg 854, 2011)

引用

JOURNAL OF MATERIALS RESEARCH 2011年第11期26卷 854-859页

作者： Cho, Sungmee Yoon, Jongsik Kim, Jung-Hyun Zhang, Xinghang Manthiram, Arumugam Wang, Haiyan [a1 ]Department of Electrical and Computer Engineering Texas A&M University College Station Texas 77843-3128[a2 ]Electrochemical Energy Laboratory and Materials Science and Engineering Program University of Texas at Austin Austin Texas 78712[a3 ]Department of Mechanical Engineering Texas A&M University College Station Texas 77843-3123[a4 ]Electrochemical Energy Laboratory and Materials Science and Engineering Program University of Texas at Austin Austin Texas 78712[a5 ]Department of Electrical and Computer Engineering Texas A&M University College Station Texas 77843-3128

Microstructural and electrical properties of Gd-doped CeO2 (GDC; Ce0.9Gd0.1O1.95) thin films prepared by pulsed laser deposition as an electrolyte in solid-oxide fuel cells (SOFCs) were investigated. The GDC thin film... 详细信息

Microstructural and electrical properties of Gd-doped CeO₂ (GDC; Ce_0.9Gd_0.1O_1.95) thin films prepared by pulsed laser deposition as an electrolyte in solid-oxide fuel cells (SOFCs) were investigated. The GDC thin films were prepared on various substrates including single-crystal yttria-stabilized zirconia (YSZ) and magnesium oxide (MgO) substrates. The GDC thin-film electrolytes with different grain sizes and grain morphologies were prepared by varying the deposition parameters, such as substrate temperature, oxygen partial pressure, target repetition rate, and laser ablation energy. The microstructural properties of these films were examined using X-ray diffraction (XRD), transmission electron microscopy (TEM), and atomic force microscopy (AFM). Alternating-current (AC) and direct-current (DC) electrical measurements through in-plane method show that the electrical property of the GDC thin film strongly depends on grain size, e.g., the total conductivity of the films deposited at 700 C (7.3 10³ S/cm) is about 20 times higher than the ones deposited at room temperature (3.6 10⁴ S/cm) at the measurement temperature of 600 C.

关键词： Thin Film Electrical Properties Physical Vapor Deposition (PVD)

来源：评论

学校读者我要写书评

暂无评论

Improving acquisition of teleoreactive logic programs through representation change

Improving acquisition of teleoreactive logic programs throug...

引用

2011 AAAI Fall Symposium

作者： Li, Nan Stracuzzi, David J. Langley, Pat Computer Science and Engineering Arizona State University Tempe AZ 85281 United States Computer Science Department Carnegie Mellon University Pittsburgh PA United States Cognitive Modeling Department Sandia National Laboratories Albuquerque NM United States

ISBN: (纸本)9781577355458

An important form of learning involves acquiring skills that let an agent achieve its goals. While there has been considerable work on learning in planning, most approaches have been sensitive to the representation of domain context, which hurts their generality. A learning mechanism that constructs skills effectively across different representations would suggest more robust behavior. In this paper, we present a novel approach to learning hierarchical task networks that acquires conceptual predicates as learning proceeds, making it less dependent on carefully crafted background knowledge. The representation acquisition procedure expands the system's knowledge about the world, and leads to more rapid learning. We show the effectiveness of the approach by comparing it with one that does not change domain representation. Copyright © 2011, Association for the Advancement of Artificial Intelligence. All rights reserved.

关键词： Mergers and acquisitions

来源：评论

学校读者我要写书评

暂无评论

Porantim-opt: Optimizing the combined selection of model-based testing techniques

Porantim-opt: Optimizing the combined selection of model-bas...

引用

Workshop on Requirements and Validation, Verification, and Testing

作者： Neto, Arilo Claudio Dias De Freitas Rodrigues, Rosiane Travassos, Guilherme Horta Post-graduation Program In Informatics Computer Science Department Federal University of Amazonas Manaus AM Brazil Systems Engineering and Computer Science Program COPPE Federal University of Rio De Janeiro Rio De Janeiro RJ Brazil

ISBN: (纸本)9780769543451

The combination of testing techniques is considered an effective strategy to evaluate a software product. However, the selection of which techniques to combine in a software project has been an interesting challenge in the Software engineering field. This paper presents a proposal extending an approach developed to support the combined selection of model-based testing (MBT) techniques, named Porantim, applying Multiobjective Combinatorial Optimization strategy by determining the smallest dominating set in a bipartite and weighted graph. Thus, a local search strategy algorithm is proposed generating solutions aiming at maximizing the coverage of software project characteristics and skills required by the testing team to use the techniques and minimizing the eventual effort to construct models used for test cases generation. A preliminary evaluation analyzes this new approach when compared to the Porantim's original version, and the results indicate improvements in the MBT techniques selection. © 2011 IEEE.

关键词： Software testing

来源：评论

学校读者我要写书评

暂无评论

Word Learning through Sensorimotor Child-Parent Interaction: A Feature Selection Approach 33

Word Learning through Sensorimotor Child-Parent Interaction:...

引用

33rd Annual Meeting of the cognitive science Society: Expanding the Space of cognitive science, CogSci 2011

作者： Yu, Chen Xu, Jun-Ming Zhu, Xiaojin Department of Psychological and Brain Sciences Cognitive Science Program Indiana University BloomingtonIN47405 United States Department of Computer Sciences University of Wisconsin-Madison MadisonWI53706 United States

ISBN: (纸本)9780976831877

This paper presents a computational model of word learning with the goal to understand the mechanisms through which word learning is grounded in multimodal social interactions between young children and their parents. We designed and implemented a novel multimodal sensing environment consisting of two head-mounted mini cameras that are placed on both the child’s and the parent’s foreheads, motion tracking of head and hand movements and recording of caregiver’s speech. Using this new sensing technology, we captured the dynamic visual information from both the learner’s perspective and the parent’s viewpoint while they were engaged in a free-play toy-naming interaction. We next implemented various data processing programs that automatically extracted visual, motion and speech features from raw sensory data. A probabilistic model was developed that can predict the child’s learning results based on sensorimotor features extracted from child-parent interaction. More importantly, through the trained regression coefficients in the model, we discovered a set of perceptual and motor patterns that are informatively time-locked to words and their intended referents and predictive of word learning. Those patterns provide quantitative measures of the roles of various sensorimotor cues that may facilitate word learning, which sheds lights on understanding the underlying real-time learning mechanisms in child-parent social interactions. © CogSci 2011.

关键词： Toys

来源：评论

学校读者我要写书评

暂无评论

Learning of Spatial Relationships between Observed and Imitated Actions allows Invariant Inverse Computation in the Frontal Mirror Neuron System

Learning of Spatial Relationships between Observed and Imita...

引用

Annual International Conference of the IEEE engineering in Medicine and Biology Society

作者： Hyuk Oh Rodolphe J. Gentili James A. Reggia Jose L. Contreras-Vidal Neuroscience and Cognitive Science Program University of Maryland Department of Kinesiology and the Neuroscience and Cognitive Science Program University of Maryland Department of Computer Science and the University of Maryland Institute for Advanced Computer Studies University of Maryland Department of Kinesiology the Neuroscience and Cognitive Science Program and the Fischell Department of Bioengineering University of Maryland

ISBN: (纸本)9781424441211

It has been suggested that the human mirror neuron system can facilitate learning by imitation through coupling of observation and action execution. During imitation of observed actions, the functional relationship between and within the inferior frontal cortex, the posterior parietal cortex, and the superior temporal sulcus can be modeled within the internal model framework. The proposed biologically plausible mirror neuron system model extends currently available models by explicitly modeling the intraparietal sulcus and the superior parietal lobule in implementing the function of a frame of reference transformation during imitation. Moreover, the model posits the ventral premotor cortex as performing an inverse computation. The simulations reveal that: i) the transformation system can learn and represent the changes in extrinsic to intrinsic coordinates when an imitator observes a demonstrator;ii) the inverse model of the imitator's frontal mirror neuron system can be trained to provide the motor plans for the imitated actions.

关键词： Mirror Neurons imitation Premotor Cortex dimensional relationship Superior parietal gyrus Superior Temporal Sulcus Intraparietal Sulcus arithmetic

来源：评论

学校读者我要写书评

暂无评论

Exploiting foveation in user-centred image fusion

Exploiting foveation in user-centred image fusion

引用

IEEE GCC Conference and Exhibition

作者： Basaeed, E. Al-Mualla, M. Vernon, D. Department of Computer Engineering Khalifa University of Science Technology and Research Sharjah United Arab Emirates Department of Robotics Brain and Cognitive Sciences Italian Institute of Technology Genoa Italy

ISBN: (纸本)9781612841199

The selection of image fusion techniques has always been a compromise between effectiveness and efficiency. In this paper, foveation (using log-polar transformation) is introduced to satisfy the real-time requirement of applications where the fused image is eventually presented to a human to interpret. Log-polar transformation achieves a data reduction without a subsequent loss in perceptual information. Thus, it can be used to reduce the execution time of any existing image fusion technique without modifying the technique itself. In this paper, the log-polar transformation is integrated with three widely-used image fusion techniques: image averaging, the Laplacian pyramid, and the Discrete Wavelet Transform. Then, the proposed fusion process is objectively evaluated using a set of established metrics;they are Mutual Information (MI), Xydas & Petrovic (QAB/F), and Piella & Heijmans (Qw). © 2011 IEEE.

关键词： Image fusion

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：