检索结果-内蒙古大学图书馆

Proceedings - 10th IEEE International Conference on computer Vision, ICCV 2005

作者： Hillel, Aharon Bar Hertz, Tomer Weinshall, Daphna School of Computer Science and Engineering Center for Neural Computation Hebrew University of Jerusalem 91904 Israel

ISBN: (纸本)076952334X

We present an efficient method for learning part-based object class models. The models include location and scale relations between parts, as well as part appearance. Models are learnt from raw object and background images, represented as an unordered set of features extracted using an interest point detector. The object class is generatively modeled using a simple Bayesian network with a central hidden node containing location and scale information, and nodes describing object parts. The model's parameters, however, are optimized to reduce a loss function which reflects training error, as in discriminative methods. Specifically, the optimization is done using a boosting-like technique with complexity linear in the number of parts and the number of features per image. This efficiency allows our method to learn relational models with many parts and features, and leads to improved results when compared with other methods. Extensive experimental results are described, using some common bench-mark datasets and three sets of newly collected data, showing the relative advantage of our method. © 2005 IEEE.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Generalization in clustering with unobserved features

Generalization in clustering with unobserved features

引用

2005 Annual Conference on neural Information Processing Systems, NIPS 2005

作者： Krupka, Eyal Tishby, Naftali School of Computer Science and Engineering Interdisciplinary Center for Neural Computation Hebrew University Jerusalem 91904 Israel

ISBN: (纸本)9780262232531

We argue that when objects are characterized by many attributes, clustering them on the basis of a relatively small random subset of these attributes can capture information on the unobserved attributes as well. Moreover, we show that under mild technical conditions, clustering the objects on the basis of such a random subset performs almost as well as clustering with the full attribute set. We prove a finite sample generalization theorems for this novel learning scheme that extends analogous results from the supervised learning setting. The scheme is demonstrated for collaborative filtering of users with movies rating as attributes.

关键词： Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

Metric learning by collapsing classes

Metric learning by collapsing classes

引用

2005 Annual Conference on neural Information Processing Systems, NIPS 2005

作者： Globerson, Amir Roweis, Sam School of Computer Science and Engineering Interdisciplinary Center for Neural Computation Hebrew University Jerusalem 91904 Israel Machine Learning Group Department of Computer Science University of Toronto Canada

ISBN: (纸本)9780262232531

We present an algorithm for learning a quadratic Gaussian metric (Mahalanobis distance) for use in classification tasks. Our method relies on the simple geometric intuition that a good metric is one under which points in the same class are simultaneously near each other and far from points in the other classes. We construct a convex optimization problem whose solution generates such a metric by trying to collapse all examples in the same class to a single point and push examples in other classes infinitely far away. We show that when the metric we learn is used in simple classifiers, it yields substantial improvements over standard alternatives on a variety of problems. We also discuss how the learned metric may be used to obtain a compact low dimensional feature representation of the original input space, allowing more efficient classification with very little reduction in performance.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Query by Committee made real

Query by Committee made real

引用

2005 Annual Conference on neural Information Processing Systems, NIPS 2005

作者： Gilad-Bachrach, Ran Navot, Amir Tishby, Naftali School of Computer Science and Engineering Hebrew University Jerusalem Israel Interdisciplinary Center for Neural Computation Hebrew University Jerusalem Israel Intel Research Israel

ISBN: (纸本)9780262232531

Training a learning algorithm is a costly task. A major goal of active learning is to reduce this cost. In this paper we introduce a new algorithm, KQBC, which is capable of actively learning large scale problems by using selective sampling. The algorithm overcomes the costly sampling step of the well known Query By Committee (QBC) algorithm by projecting onto a low dimensional space. KQBC also enables the use of kernels, providing a simple way of extending QBC to the non-linear scenario. Sampling the low dimension space is done using the hit and run random walk. We demonstrate the success of this novel algorithm by applying it to both artificial and a real world problems.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

A temporal kernel-based model for tracking hand-movements from neural activities

A temporal kernel-based model for tracking hand-movements fr...

引用

18th Annual Conference on neural Information Processing Systems, NIPS 2004

作者： Shpigelman, Lavi Crammer, Koby Paz, Rony Vaadia, Eilon Singer, Yoram School of Computer Science and Engineering Israel Interdisciplinary Center for Neural Computation Israel Dept. of Physiology Hadassah Medical School Hebrew University Jerusalem 91904 Israel

ISBN: (纸本)0262195348

We devise and experiment with a dynamical kernel-based system for tracking hand movements from neural activity. The state of the system corresponds to the hand location, velocity, and acceleration, while the system's input are the instantaneous spike rates. The system's state dynamics is defined as a combination of a linear mapping from the previous estimated state and a kernel-based mapping tailored for modeling neural activities. In contrast to generative models, the activity-to-state mapping is learned using discriminative methods by minimizing a noise-robust loss function. We use this approach to predict hand trajectories on the basis of neural activity in motor cortex of behaving monkeys and find that the proposed approach is more accurate than both a static approach based on support vector regression and the Kalman filter.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

A meshfree method and its applications to elasto-plastic problems

引用

Journal of Zhejiang University-science A(Applied Physics & engineering) 2005年第2期6卷 148-154页

作者：张继发张文普郑耀 Center for Engineering and Scientific Computation School of Computer Science Zhejiang University Hangzhou 310027 China Center for Engineering and Scientific Computation Department of Mechanics

Standard finite element approaches are still ineffective in handling extreme material deformation, such as cases of large deformations and moving discontinuities due to severe mesh distortion. Among meshfree methods developed to overcome the ineffectiveness, Reproducing Kernel Particle Method (RKPM) has demonstrated its great suitability for structural *** paper presents applications of RKPM in elasto-plastic problems after a review of meshfree methods and an introduction to RKPM. A slope stability problem in geotechnical engineering is analyzed as an illustrative case. The corresponding numerical simulations are carried out on an SGI Onyx3900 supercomputer. Comparison of the RKPM and the FEM under identical conditions showed that the RKPM is more suitable for problems where there exists extremely large strain such as in the case of slope sliding.

关键词： Meshfree methods RKPM Elasto-plasticity Geotechnical engineering

来源：评论

学校读者我要写书评

暂无评论

Spike sorting: Bayesian clustering of non-stationary data

Spike sorting: Bayesian clustering of non-stationary data

引用

18th Annual Conference on neural Information Processing Systems, NIPS 2004

作者： Bar-Hillel, Aharon Spiro, Adam Stark, Eran Neural Computation Center Hebrew University of Jerusalem Israel School of Computer Science and Engineering Hebrew University of Jerusalem Israel Department of Physiology Hebrew University of Jerusalem Israel

ISBN: (纸本)0262195348

Spike sorting involves clustering spike trains recorded by a microelectrode according to the source neuron. It is a complicated problem, which requires a lot of human labor, partly due to the non-stationary nature of the data. We propose an automated technique for the clustering of non-stationary Gaussian sources in a Bayesian framework. At a first search stage, data is divided into short time frames and candidate descriptions of the data as a mixture of Gaussians are computed for each frame. At a second stage transition probabilities between candidate mixtures are computed, and a globally optimal clustering is found as the MAP solution of the resulting probabilistic model. Transition probabilities are computed using local stationarity assumptions and are based on a Gaussian version of the Jensen-Shannon divergence. The method was applied to several recordings. The performance appeared almost indistinguishable from humans in a wide range of scenarios, including movement, merges, and splits of clusters.

关键词： Microelectrodes

来源：评论

学校读者我要写书评

暂无评论

Euclidean embedding of co-occurrence data

Euclidean embedding of co-occurrence data

引用

18th Annual Conference on neural Information Processing Systems, NIPS 2004

作者： Globerson, Amir Chechik, Gal Pereira, Fernando Tishby, Naftali Interdisciplinary Center for Neural Computation School of Computer Science and Engineering Hebrew University Jerusalem 91904 Jerusalem Israel Computer Science Department Stanford University Stanford CA 94305 United States Department of Computer and Information Science University of Pennsylvania Philadelphia PA 19104 United States

ISBN: (纸本)0262195348

Embedding algorithms search for low dimensional structure in complex data, but most algorithms only handle objects of a single type for which pairwise distances are specified. This paper describes a method for embedding objects of different types, such as images and text, into a single common Euclidean space based on their co-occurrence statistics. The joint distributions are modeled as exponentials of Euclidean distances in the low-dimensional embedding space, which links the problem to convex optimization over positive semidefinite matrices. The local structure of our embedding corresponds to the statistical correlations via random walks in the Euclidean space. We quantify the performance of our method on two text datasets, and show that it consistently and significantly outperforms standard methods of statistical correspondence modeling, such as multidimensional scaling and correspondence analysis.

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

Efficient learning of relational object class models

Efficient learning of relational object class models

引用

International Conference on computer Vision (ICCV)

作者： A.B. Hillel D. Weinshall T. Hertz School of Computer Science and Engineering and the Center for Neural Computation Hebrew university of Jerusalem Israel

We present an efficient method for learning part-based object class models. The models include location and scale relations between parts, as well as part appearance. Models are learnt from raw object and background images, represented as an unordered set of features extracted using an interest point detector. The object class is generatively modeled using a simple Bayesian network with a central hidden node containing location and scale information, and nodes describing object parts. The model's parameters, however are optimized to reduce a loss function which reflects training error as in discriminative methods. Specifically, the optimization is done using a boosting-like technique with complexity linear in the number of parts and the number of features per image. This efficiency allows our method to learn relational models with many parts and features, and leads to improved results when compared with other methods. Extensive experimental results are described, using some common bench-mark datasets and three sets of newly collected data, showing the relative advantage of our method

关键词： Bayesian methods Optimization methods Object recognition computer science Feature extraction Data mining Object detection Detectors Humans Lighting

来源：评论

学校读者我要写书评

暂无评论

Analyzing auditory neurons by learning distance functions

Analyzing auditory neurons by learning distance functions

引用

2005 Annual Conference on neural Information Processing Systems, NIPS 2005

作者： Weiner, Inna Hertz, Tomer Nelken, Israel Weinshall, Daphna School of Computer Science and Engineering Hebrew University of Jerusalem Jerusalem 91904 Israel Center for Neural Computation Hebrew University of Jerusalem Jerusalem 91904 Israel Department of Neurobiology Hebrew University of Jerusalem Jerusalem 91904 Israel

ISBN: (纸本)9780262232531

We present a novel approach to the characterization of complex sensory neurons. One of the main goals of characterizing sensory neurons is to characterize dimensions in stimulus space to which the neurons are highly sensitive (causing large gradients in the neural responses) or alternatively dimensions in stimulus space to which the neuronal response are invariant (defining iso-response manifolds). We formulate this problem as that of learning a geometry on stimulus space that is compatible with the neural responses: the distance between stimuli should be large when the responses they evoke are very different, and small when the responses they evoke are similar. Here we show how to successfully train such distance functions using rather limited amount of information. The data consisted of the responses of neurons in primary auditory cortex (A1) of anesthetized cats to 32 stimuli derived from natural sounds. For each neuron, a subset of all pairs of stimuli was selected such that the responses of the two stimuli in a pair were either very similar or very dissimilar. The distance function was trained to fit these constraints. The resulting distance functions generalized to predict the distances between the responses of a test stimulus and the trained stimuli.

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：