检索结果-内蒙古大学图书馆

IEEE Workshop on Machine Learning for Signal Processing

作者： Shahriar Shariat Vladimir Pavlovic Thomas Papathomas Ainsley Braun Pawan Sinha Department Computer Science Rutgers University Piscataway NJ USA Department of Biomedical Engineering and RuCCS/Lab of Vision Research Rutgers University Piscataway NJ USA Department of Brain and Cognitive Sciences MIT Cambridge MA USA

This paper presents a systematic application of machine learning techniques for classifying high-density EEG signals elicited by face and non-face stimuli. The two stimuli used here are derived from the vase-faces illusion and share the same defining contours, differing only slightly in stimulus space. This emphasizes activity differences related to high-level percepts rather than low-level attributes. This design decision results in a difficult classification task for the ensuing EEG signals. Traditionally, EEG analyses are done on the basis of signal processing techniques involving multiple instance averaging and then a manual examination to detect differentiating components. The present study constitutes an agnostic effort based on purely statistical estimates of three major classifiers: L1-norm logistic regression, group lasso and k Nearest Neighbors (kNN); kNN produced the worst results. L1 regression and group lasso show significantly better performance, while being abl e to identify distinct spatio-temporal signatures. Both L1 regression and group lasso assert the saliency of samples in 170ms, 250ms, 400ms and 600ms after stimulus onset, congruent with the previously reported ERP components associated with face perception. Similarly, spatial locations of salient markers point to the occipital and temporal brain regions, previously implicated in visual object perception. The overall approach presented here can provide a principled way of identifying EEG correlates of other perceptual/cognitive tasks.

关键词： Face Electroencephalography Logistics brain models Visualization Dictionaries

来源：评论

学校读者我要写书评

暂无评论

Structured Local Binary Haar pattern for graphics retrieval

Structured Local Binary Haar pattern for graphics retrieval

引用

IEEE International Conference on Intelligent Computing and Intelligent Systems (ICIS)

作者： Song-Zhi Su Shu-Yuan Chen Shang-An Li Shao-Zi Li Der-Jyh Duh Cognitive Science Department of Xiamen University Fujian Key Laboratory of the Brain-like Intelligent Systems (Xiamen University) Xiamen China Yuan-Ze University Taiwan Xiamen University Xiamen China Department of Computer Engineering and Science of Yuan-Ze University Taiwan Xiamen University Xiamen Fujian CN Ching-Yun University Taiwan

Feature extraction is an important issue in graphics retrieval. Local feature based descriptors are currently the predominate method used in image retrieval and object recognition. Inspired by the success of Haar feature and Local Binary Pattern (LBP), a novel feature named structured local binary Haar pattern (SLBHP) is proposed for graphics retrieval in this paper. SLBHP encodes the polarity instead of the magnitude of the difference between accumulated gray values of adjacent rectangles. Experimental results on graphics retrieval show that the discriminative power of SLBHP is better than those of using edge points (EP), Haar feature, and LBP even in noisy condition.

关键词： Image recognition

来源：评论

学校读者我要写书评

暂无评论

Dependence of orientation tuning on recurrent excitation and inhibition in a network model of V1

Dependence of orientation tuning on recurrent excitation and...

引用

22nd Annual Conference on Neural Information Processing Systems, NIPS 2008

作者： Wimmer, Klaus Stimberg, Marcel Martin, Robert Schwabe, Lars Mariño, Jorge Schummers, James Lyon, David C. Sur, Mriganka Obermayer, Klaus Bernstein Center for Computational Neuroscience Technische Universität Berlin Germany Dept of Computer Science and Electrical Engineering University of Rostock Germany Dept of Medicine Neuroscience and Motor Control Group Univ. A Coruña Spain Dept of Brain and Cognitive Sci Picower Ctr for Learning and Memory MIT Cambridge United States Dept of Anatomy and Neurobiology University of California Irvine United States

ISBN: (纸本)9781605609492

The computational role of the local recurrent network in primary visual cortex is still a matter of debate. To address this issue, we analyze intracellular recording data of cat V1, which combine measuring the tuning of a range of neuronal properties with a precise localization of the recording sites in the orientation preference map. For the analysis, we consider a network model of Hodgkin-Huxley type neurons arranged according to a biologically plausible two-dimensional topographic orientation preference map. We then systematically vary the strength of the recurrent excitation and inhibition relative to the strength of the afferent input. Each parametrization gives rise to a different model instance for which the tuning of model neurons at different locations of the orientation map is compared to the experimentally measured orientation tuning of membrane potential, spike output, excitatory, and inhibitory conductances. A quantitative analysis shows that the data provides strong evidence for a network model in which the afferent input is dominated by strong, balanced contributions of recurrent excitation and inhibition. This recurrent regime is close to a regime of "instability", where strong, self-sustained activity of the network occurs. The firing rate of neurons in the best-fitting network is particularly sensitive to small modulations of model parameters, which could be one of the functional benefits of a network operating in this particular regime.

关键词： Neurons

来源：评论

学校读者我要写书评

暂无评论

Directed information structure in inter-regional cortical interactions in a visuomotor tracking task

引用

BMC Neuroscience 2009年第1期10卷 1-2页

作者： Joseph T Lizier Mikhail Prokopenko John-Dylan Haynes Jakob Heinzle School of Information Technologies The University of Sydney NSW 2006 Australia School of Computer Science and Engineering The University of New South Wales NSW 2052 Australia Bernstein Center for Computational Neuroscience Charité-Universitätsmedizin Berlin Philippstrasse 13 Haus 6 10115 Berlin Germany Max Planck Institute for Human Cognitive and Brain Sciences Stephanstrasse 1A 04103 Leipzig Germany

来源：评论

学校读者我要写书评

暂无评论

A biomimetic adaptive algorithm and low-power architecture for implantable neural decoders

A biomimetic adaptive algorithm and low-power architecture f...

引用

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

作者： Benjamin I. Rapoport Woradorn Wattanapanitch Hector L. Penagos Sam Musallam Richard A. Andersen Rahul Sarpeshkar Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology Cambridge MA USA Harvard-MIT Division of Health Sciences and Technology Harvard Medical School Cambridge MA USA MIT Department of Brain and Cognitive Sciences and the Harvard-MIT Division Health Sciences and Technology USA Department of Electrical and Computer Engineering McGill University Montreal QUE Canada Division of Biology California Institute of Technology Pasadena CA USA

Algorithmically and energetically efficient computational architectures that operate in real time are essential for clinically useful neural prosthetic devices. Such devices decode raw neural data to obtain direct control signals for external devices. They can also perform data compression and vastly reduce the bandwidth and consequently power expended in wireless transmission of raw data from implantable brain-machine interfaces. We describe a biomimetic algorithm and micropower analog circuit architecture for decoding neural cell ensemble signals. The decoding algorithm implements a continuous-time artificial neural network, using a bank of adaptive linear filters with kernels that emulate synaptic dynamics. The filters transform neural signal inputs into control-parameter outputs, and can be tuned automatically in an on-line learning process. We provide experimental validation of our system using neural data from thalamic head-direction cells in an awake behaving rat.

关键词： Biomimetics Adaptive algorithm Decoding computer architecture Nonlinear filters Prosthetics Data compression Bandwidth Analog circuits Artificial neural networks

来源：评论

学校读者我要写书评

暂无评论

Unsupervised learning of overlapping image components using divisive input modulation

引用

Computational Intelligence and Neuroscience 2009年第1期2009卷 381457页

作者： Spratling, M.W. De Meyer, K. Kompass, R. Division of Engineering King's College London London WC2R 2LS United Kingdom Centre for Brain and Cognitive Development Birkbeck College University of London London WC1E 7HX United Kingdom Artificial Intelligence Group Institute of Computer Science Freie Universitt Berlin 14195 Berlin Germany

This paper demonstrates that nonnegative matrix factorisation is mathematically related to a class of neural networks that employ negative feedback as a mechanism of competition. This observation inspires a novel learning algorithm which we call Divisive Input Modulation (DIM). The proposed algorithm provides a mathematically simple and computationally efficient method for the unsupervised learning of image components, even in conditions where these elementary features overlap considerably. To test the proposed algorithm, a novel artificial task is introduced which is similar to the frequently-used bars problem but employs squares rather than bars to increase the degree of overlap between components. Using this task, we investigate how the proposed method performs on the parsing of artificial images composed of overlapping features, given the correct representation of the individual components;and secondly, we investigate how well it can learn the elementary components from artificial training images. We compare the performance of the proposed algorithm with its predecessors including variations on these algorithms that have produced state-of-the-art performance on the bars problem. The proposed algorithm is more successful than its predecessors in dealing with overlap and occlusion in the artificial task that has been used to assess performance. Copyright © 2009 M.W. Spratling et al.

关键词：

来源：评论

学校读者我要写书评

暂无评论

cognitive learning and the multimodal memory game: Toward human-level machine learning

Cognitive learning and the multimodal memory game: Toward hu...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Byoung-Tak Zhang School of Computer Science and Engineering and Graduate Programs in Cognitive Science Brain Science and Bioinformatics Seoul National University Seoul South Korea

Machine learning has made great progress during the last decades and is being deployed in a wide range of applications. However, current machine learning techniques are far from sufficient for achieving human-level intelligence. Here we identify the properties of learners required for human-level intelligence and suggest a new direction of machine learning research, i.e. the cognitive learning approach, that takes into account the recent findings in brain and cognitive sciences. In particular, we suggest two fundamental principles to achieve human-level machine learning: continuity (forming a lifelong memory continuously) and glocality (organizing a plastic structure of localized micromodules connected globally). We then propose a multimodal memory game as a research platform to study cognitive learning architectures and algorithms, where the machine learner and two human players question and answer about the scenes and dialogues after watching the movies. Concrete experimental results are presented to illustrate the usefulness of the game and the cognitive learning framework for studying human-level learning and intelligence.

关键词： Games Machine learning Humans Motion pictures Machine learning algorithms Joints Chemistry

来源：评论

学校读者我要写书评

暂无评论

Dependence of orientation tuning on recurrent excitation and inhibition in a network model of V1 08

Dependence of orientation tuning on recurrent excitation and...

引用

Proceedings of the 22nd International Conference on Neural Information Processing Systems

作者： Klaus Wimmer Marcel Stimberg Robert Martin Lars Schwabe Jorge Mariño James Schummers David C. Lyon Mriganka Sur Klaus Obermayer Bernstein Center for Computational Neuroscience and Technische Universität Berlin Germany Dept of Computer Science and Electrical Engineering University of Rostock Germany Dept of Medicine Neuroscience and Motor Control Group Univ. A Coruña Spain Dept of Brain and Cognitive Sci and Picower Ctr for Learning and Memory MIT Cambridge Dept of Anatomy and Neurobiology University of California Irvine

ISBN: (纸本)9781605609492

关键词：

来源：评论

学校读者我要写书评

暂无评论

Random Hypergraph Models of Learning and Memory in Biomolecular Networks: Shorter-Term Adaptability vs. Longer-Term Persistency

Random Hypergraph Models of Learning and Memory in Biomolecu...

引用

IEEE Symposium on Foundations of Computational Intelligence, FOCI

作者： Byoung-Tak Zhang School of Computer Science and Engineering Brain Science and Cognitive Science Seoul National University Seoul South Korea

Recent progress in genomics and proteomics makes it possible to understand the biological networks at the systems level. We aim to develop computational models of learning and memory inspired by the biomolecular networks embedded in their environment. One fundamental question is how the systems rapidly adapt to their changing environment in a short period (learning) while performing persistently through the longer time span (memory). We study this issue in a probabilistic hypergraph model called the hypernetworks. The hypernetwork architecture consists of a huge number of randomly sampled hyperedges, each corresponding to higher-order micromodules in the input. We find that a system consisting of a large number of a wide range of heterogeneous low-dimensional components has a fairly competitive chance of long-term survival (memory, persistency) and short-term performance (learning, adaptability) as opposed to a system consisting of a small number of high-dimensional, fine-tuned, complex components. Empirical evidence is offered to support these findings and theoretical explanations are given

关键词： Bioinformatics Information processing Organisms Biological system modeling Genomics Proteomics Biology computing computer networks Computational intelligence Embedded computing

来源：评论

学校读者我要写书评

暂无评论

Language Understanding and Unified cognitive science

Language Understanding and Unified Cognitive Science

引用

IEEE International Conference on cognitive Informatics

作者： Jerry A. Feldman Department of Electrical Engineering and Computer Science Institute of Cognitive and Brain Sciences University of California Berkeley Berkeley CA USA

Summary form only given. Artificial intelligence applications, particularly those involving natural language understanding, are actually less ambitious than they, were decades ago. Statistical and machine learning techniques have had great success on tasks that can be treated without understanding, but there are many important areas that require semantic systems. The key to building more powerful AI applications is to model the world knowledge and the linguistic and other basic abilities that people bring to bear. We now know that these abilities can not be fully expressed in abstract formalisms, but require models that map onto human biology and behavior. cognitive science is the field that is best placed to unite the theory and applications of intelligence. However, as with other fields, there is a tendency to specialize in a narrow sub-domain. This talk will make the case that a unified cognitive science is now possible, based on rapid advances in all the relevant disciplines, including computational modeling, and that there are already applications of this more cognitive approach to AI.

关键词： cognitive science Artificial intelligence Biological system modeling Power system modeling Natural languages Machine learning Humans Computational biology Computational intelligence Computational modeling

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：