检索结果-内蒙古大学图书馆

International Joint Conference on Neural Networks (IJCNN)

作者： H. Liljenstrom X.B. Wu SANS-Studies of Artificial Neural Systems Department of Numerical Analysis and Computing Science Royal Institute of Technology Stockholm Sweden

We study the role of complex neurodynamics in learning and associative memory using a neural network model of the olfactory cortex. By varying the noise level and a control parameter, corresponding to the level of neuromodulator or arousal, we analyze the resulting nonlinear dynamics during learning and recall of constant and oscillatory input. Point attractor, limit cycle, and strange attractor dynamics occur at different values of the control parameter. We show that oscillations and chaos-like behavior can give shorter recall times and more robust memory states than in static cases. In particular, we show that the recall time can reach a minimum for additive and multiplicative noise. Also noise-induced state transitions and noise-induced chaos-like behavior is demonstrated.< >

关键词： Associative memory Chaos Additive noise Neurodynamics Neural networks Brain modeling Olfactory Noise level Limit-cycles Noise robustness

来源：评论

学校读者我要写书评

暂无评论

A flexible and fault tolerant query-reply system based on a Bayesian neural network.

引用

International journal of neural systems 1993年第3期4卷 257-267页

作者： Holst, A. Lansner, A. Department of Numerical Analysis and Computing Science Royal Institute of Technology Stockholm Sweden

A query-reply system based on a Bayesian neural network is described. Strategies for generating questions which make the system both efficient and highly fault tolerant are presented. This involves having one phase of question generation intended to quickly reach a hypothesis followed by a phase where verification of the hypothesis is attempted. In addition, both phases have strategies for detecting and removing inconsistencies in the replies from the user. Also described is an explanatory mechanism which gives information related to why a certain hypotheses is reached or question asked. Specific examples of the systems behavior as well as the results of a statistical evaluation are presented.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Discrete derivative approximations with scale-space properties. A basis for low-level feature extraction

引用

Journal of Mathematical Imaging and Vision 1993年第4期3卷 349-349页

作者： Lindeberg, Tony Department of Numerical Analysis and Computing Science Royal Institute of Technology Computational Vision and Active Perception Laboratory Stockholm Sweden

This article shows how discrete derivative approximations can be defined so thatscale-space properties hold exactly also in the discrete domain. Starting from a set of natural requirements on the first processing stages of a visual system,the visual front end, it gives an axiomatic derivation of how a multiscale representation of derivative approximations can be constructed from a discrete signal, so that it possesses analgebraic structure similar to that possessed by the derivatives of the traditional scale-space representation in the continuous domain. A family of kernels is derived that constitutediscrete analogues to the continuous Gaussian derivatives. The representation has theoretical advantages over other discretizations of the scale-space theory in the sense that operators that commute before discretizationcommute after discretization. Some computational implications of this are that derivative approximations can be computeddirectly from smoothed data and that this will giveexactly the same result as convolution with the corresponding derivative approximation kernel. Moreover, a number ofnormalization conditions are automatically satisfied. The proposed methodology leads to a scheme of computations of multiscale low-level feature extraction that is conceptually very simple and consists of four basic steps: (i)large support convolution smoothing, (ii)small support difference computations, (iii)point operations for computing differential geometric entities, and (iv)nearest-neighbour operations for feature detection. Applications demonstrate how the proposed scheme can be used for edge detection and junction detection based on derivatives up to order three.

关键词： computer vision digital signal processing discrete approximation edge detection Gaussian derivative Gaussian filtering junction detection multiscale representation scale-space smoothing visual front end

来源：评论

学校读者我要写书评

暂无评论

DETECTING SALIENT BLOB-LIKE IMAGE STRUCTURES AND THEIR SCALES WITH A SCALE-SPACE PRIMAL SKETCH - A METHOD FOR FOCUS-OF-ATTENTION

引用

INTERNATIONAL JOURNAL OF COMPUTER VISION 1993年第3期11卷 283-318页

作者： LINDEBERG, T 1. Computational Vision and Active Perception Laboratory (CVAP) Department of Numerical Analysis and Computing Science Royal Institute of Technology S-100 44 Stockholm Sweden

This article presents: (i) a multiscale representation of grey-level shape called the scale-space primal sketch, which makes explicit both features in scale-space and the relations between structures at different scales, (ii) a methodology for extracting significant blob-like image structures from this representation, and (iii) applications to edge detection, histogram analysis, and junction classification demonstrating how the proposed method can be used for guiding later-stage visual processes. The representation gives a qualitative description of image structure, which allows for detection of stable scales and associated regions of interest in a solely bottom-up data-driven way. In other words, it generates coarse segmentation cues, and can hence be seen as preceding further processing, which can then be properly tuned. It is argued that once such information is available, many other processing tasks can become much simpler. Experiments on real imagery demonstrate that the proposed theory gives intuitive results.

关键词： Dermal denticles Explicit Sketches BALANCES images Scale squama visual processing Imagery (Psychotherapy) Image IMAGE STRUCTURE scales

来源：评论

学校读者我要写书评

暂无评论

Polynomially bounded minimization problems which are hard to approximate 20th

引用

20th International Colloquium on Automata, Languages and Programming, ICALP 1993

作者： Kann, Viggo Department of Numerical Analysis and Computing Science Royal Institute of Technology StockholmS-100 44 Sweden

ISBN: (纸本)9783540569398

MIN PB is the class of minimization problems whose objective functions are bounded by a polynomial in the size of the input. We show that there exist several problems which are MIN PB-complete with respect to an approximation preserving reduction. These problems are very hard to approximate;in polynomial time they cannot be approximated within nΕ for some Ε > 0, where n is the size of the input, provided that P ≠ NP. In particular, the problem of finding the minimum independent dominating set in a graph, the problem of satisfying a 3-SAT formula setting the least number of variables to one, and the minimum bounded 0-1 programming problem are shown to be MIN PB-complete. We also present a new type of approximation preserving reduction that is designed for problems whose approximabflity is expressed as a function in some size parameter. Using this reduction we obtain good lower bounds on the approximability of the treated problems. © Springer-Verlag Berlin Heidelberg 1993.

关键词： Polynomial approximation

来源：评论

学校读者我要写书评

暂无评论

Response properties of a population of neurons.

引用

International journal of neural systems 1993年第1期4卷 1-13页

作者： Ekeberg, O. SANS-Studies of Artificial Neural Systems Dept. of Numerical Analysis and Computing Science Royal Institute of Technology Stockholm Sweden

This work is concerned with the question of how a population of neurons responds to tonic and transient synaptic input from other similar populations. Because of the methodological problems involved in measuring and manipulating the firing properties of a large set of real neurons simultaneously, another strategy is used here: the experiments are made as a series of simulations using a population of realistic model neurons. The steady state response of this particular model neuron is found to be similar to that used in abstract nonspiking models. The transient response, however, reveals that even though each individual neuron simply changes its frequency moderately, the population can respond quickly and with damped oscillations. These oscillations are due to spike synchronization caused by systematic phase shifts induced by synchronous changes in the input.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The paper model for computer-based writing 93

The paper model for computer-based writing

引用

Proceedings of the INTERACT '93 and CHI '93 Conference on Human Factors in computing Systems

作者： Ann Fatton Staffan Romberger Kerstin Severinson Eklundh IPLab Department of Numerical Analysis and Computing Science Royal Institute of Technology S-100 44 Stockholm Sweden

No abstract available.

ISBN: (纸本)9780897915755

No abstract available.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Simulated neuromodulatory effects on the nonlinear dynamics of olfactory cortex

Simulated neuromodulatory effects on the nonlinear dynamics ...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： H. Liljenstrom X.B. Wu Department of Numerical Analysis and Computing Science Royal Institute of Technology SANS Studies of Artijicial Neural Systems Stockholm Sweden

The dynamic behavior of cortical structures can change significantly in character by different types of neuromodulators. We simulate such effects in a neural network model of the olfactory cortex and analyze the resulting nonlinear dynamics of this system. The model uses simple network units and a network connectivity which closely resembles that of the real cortex. The input-output relation of populations of neurons is represented as a sigmoid function, with a single parameter determining threshold, slope and amplitude of the curve. This parameter is taken to correspond to the level of neuromodulator and correlated with the level of arousal of an animal. By varying this "gain parameter" we show that the model can give point attractor, limit cycle attractor and strange chaotic or nonchaotic attractor behavior. We also display "transient chaos", which begins with chaos-like behavior but eventually goes to a limit cycle. We show how this complex dynamics is related to learning and associative memory in our system and discuss the biological significance of this.

关键词： Brain modeling Olfactory Nonlinear dynamical systems Chaos Limit-cycles Analytical models Neural networks Neurons Animals Displays

来源：评论

学校读者我要写书评

暂无评论

Invariance constraints for improving generalization in probabilistic neural networks

Invariance constraints for improving generalization in proba...

引用

International Conference on Neural Networks

作者： H.G.C. Traven Studies of Artificial Neural Systems (SANS) research group Department of Numerical Analysis and Computing Science (NADA) Royal Institute of Technology Stockholm Sweden

Probabilistic neural networks can approximate class conditional densities in optimal (Bayesian) pattern classifiers. In natural pattern recognition applications, the size of the training set is always limited, making the approximation task difficult. Invariance constraints can significantly simplify the task of density approximation. A technique is presented for learning invariant representations, based on a statistical approach to ground invariance. An iterative method is developed formally for computing the maximum likelihood estimate to the parameters of an invariant mixture model. The method can be interpreted as a competitive training strategy for a radial basis function (RBF) network. It can be used for self-organizing formation of both invariant templates and features.< >

关键词： Intelligent networks Neural networks Artificial neural networks Pattern recognition Computer networks Bayesian methods Storage area networks numerical analysis Parameter estimation Organizing

来源：评论

学校读者我要写书评

暂无评论

Integrating task-directed plaiming with reactive object recognition 12

Integrating task-directed plaiming with reactive object reco...

引用

Intelligent Robots and Computer Vision XII: Algorithms and Techniques 1993

作者： Dickinson, Sven Stevenson, Suzanne Amdur, Eugene Tsotsos, John Olsson, Lars Department of Computer Science University of Toronto 6 King's College Rd. TorontoONM5S1A4 Canada Computational Vision and Active Perception Laboratory Dept. of Numerical Analysis and Computing Science Royal Institute of Tecimology StockholmS-10044 Sweden

We describe a robot vision system that achieves complex object recognition with two layers of behaviors, performing the tasks of planning and object recognition, respectively. The recognition layer is a pipeline in which successive stages take in images from a stereo head, recover relevant features, build intermediate representations, and deposit 3-D objects into a world model. Each stage is an independent process that reacts automatically to output from the previous stage. This reactive system operates continuously and autonomously to construct the robot's 3-D model of the environment. Sitting above the recognition pipeline is the planner which is responsible for populating the world model with objects that satisfy the high-level goals of the system. For example, upon examination of the world model, the planner can decide to direct the head to another location, gating new images into the recognition pipeline, causing new objects to be deposited into the world model. Alternatively, the planner can alter the recognition behavior of the pipeline so that objects of a certain type or at a certain location appear in the world model. © 1993 SPIE.

关键词： Pipelines

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：