检索结果-内蒙古大学图书馆

International Joint Conference on Neural Networks (IJCNN)

作者： M. Ventresca H.R. Tizhoosh Pattern Analysis and Machine Intelligence (PAMI) laboratory in the Systems Design Engineering Department University of Waterloo Waterloo ONT Canada

The backpropagation algorithm is a very popular approach to learning in feed-forward multi-layer perceptron networks. However, in many scenarios the time required to adequately learn the task is considerable. Many existing approaches have improved the convergence rate by altering the learning algorithm. We present a simple alternative approach inspired by opposition-based learning that simultaneously considers each network transfer function and its opposite. The effect is an improvement in convergence rate and over traditional backpropagation learning with momentum. We use four common benchmark problems to illustrate the improvement in convergence time.

关键词： Convergence Transfer functions Neural networks Backpropagation algorithms Genetic algorithms pattern analysis machine intelligence Laboratories System analysis and design design engineering

来源：评论

学校读者我要写书评

暂无评论

Increasing Object Recognition Rate using Reinforced Segmentation

Increasing Object Recognition Rate using Reinforced Segmenta...

引用

IEEE International Conference on Image Processing

作者： Farhang Sahba Hamid R. Tizhoosh Magdy M.A. Salama Systems Design Engineering University of Waterloo Waterloo ONT Canada Electrical and Computer Engineering Pattern Analysis and Machine Intelligence Laboratory Waterloo ONT Canada

In this paper a new approach to object extraction and recognition based on reinforcement learning is presented. We use this novel idea as a method to optimally segment the image and increase the recognition rate. The ... 详细信息

关键词： Object recognition Learning Image segmentation Data mining design engineering pattern analysis machine intelligence Laboratories Image recognition Object detection

来源：评论

学校读者我要写书评

暂无评论

A Reinforcement Learning Framework for Medical Image Segmentation

A Reinforcement Learning Framework for Medical Image Segment...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： F. Sahba H.R. Tizhoosh M.M.A. Salama Pattern Analysis and Machine Intelligence Laboratory Department of System Design Engineering University of Waterloo Waterloo ONT Canada Department of Electrical and Computer Engineering University of Waterloo Waterloo ONT Canada

This paper introduces a new method to medical image segmentation using a reinforcement learning scheme. We use this novel idea as an effective way to optimally find the appropriate local thresholding and structuring element values and segment the prostate in ultrasound images. Reinforcement learning agent uses an ultrasound image and its manually segmented version and takes some actions (i.e., different thresholding and structuring element values) to change the environment (the quality of segmented image). The agent is provided with a scalar reinforcement signal determined objectively. The agent uses these objective reward/punishment to explore/exploit the solution space. The values obtained using this way can be used as valuable knowledge to fill a Q-matrix. The reinforcement learning agent can use this knowledge for similar ultrasound images as well. The results demonstrate high potential for applying reinforcement learning in the field of medical image segmentation.

关键词： Learning Biomedical imaging Image segmentation Ultrasonic imaging Medical diagnostic imaging pattern analysis machine intelligence Laboratories System analysis and design design engineering

来源：评论

学校读者我要写书评

暂无评论

Cooperation: Concepts and General Typology

Cooperation: Concepts and General Typology

引用

IEEE International Conference on systems, Man and Cybernetics

作者： Alaa M. Khamis Mohamed S. Kamel Miguel A. Salichs Pattern Analysis and Machine Intelligence (PAMI) Laboratory University of Waterloo Canada RoboticsLab Department of Systems Engineering and Automation Carlos III Technical University of Madrid Spain PAMI Laboratory Electrical and Computer Engineering Department University of Waterloo Canada

Life on this planet is full of astonishing examples of cooperation. Individual species depend upon one another for sustenance, often forming surprising alliances to achieve a common goal: continuance of the species. The majority of living things also display amazing altruism in order to protect and provide the best care for their offspring, incomparable to any form of sacrifice shown by human beings. Studying the cooperation patterns between living things and their intelligent behaviors has been source of inspiration for many new algorithms, theories and systems. This paper addresses the concept of cooperation and why it is important. It highlights the available biologically-inspired models and algorithms, and their potential applications. The paper also presents a general typology of cooperation patterns, which can help to understand how systems could work cooperatively in an intelligent manner.

关键词： Intelligent systems Biological system modeling Intelligent robots Artificial intelligence Cybernetics Planets Displays Protection Humans Multiagent systems

来源：评论

学校读者我要写书评

暂无评论

Search Space analysis of Recurrent Spiking and Continuous-time Neural Networks

Search Space Analysis of Recurrent Spiking and Continuous-ti...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： M. Ventresca B. Ombuki Systems Design Engineering and member of the Pattern Analysis and Machine Intelligence Laboratory University of Waterloo Waterloo ONT Canada Department of Computing and Information Science University of Guelph Guelph ONT Canada Computer Science Department Brock University Saint Catharines ONT Canada

The problem of designing recurrent continuous-time and spiking neural networks is NP-Hard. A common practice is to utilize stochastic searches, such as evolutionary algorithms, to automatically construct acceptable networks. The outcome of the stochastic search is related to its ability to navigate the search space of neural networks and discover those of high quality. In this paper we investigate the search space associated with designing the above recurrent neural networks in order to differentiate which network should be easier to automatically design via a stochastic search. Our investigation utilizes two popular dynamic systems problems; (1) the Henon map and (2) the inverted pendulum as a benchmark.

关键词： Neural networks Recurrent neural networks Stochastic processes Chaotic communication Neurons Biological system modeling Evolutionary computation Navigation Helium Visualization

来源：评论

学校读者我要写书评

暂无评论

Opposition-Based Learning: A New Scheme for machine intelligence

Opposition-Based Learning: A New Scheme for Machine Intellig...

引用

International Conference on Computational intelligence for Modelling, Control and Automation, and International Conference on Intelligent Agents, Web Technologies and Internet Commerce

作者： H.R. Tizhoosh Pattern Analysis and Machine Intelligence Lab Systems Design Engineering University of Waterloo Waterloo ONT Canada

Opposition-based learning as a new scheme for machine intelligence is introduced. Estimates and counter-estimates, weights and opposite weights, and actions versus counter-actions are the foundation of this new approach. Examples are provided. Possibilities for extensions of existing learning algorithms are discussed. Preliminary results are provided

关键词： machine learning machine intelligence Genetic algorithms Intelligent agent Neural networks Internet Biological neural networks Humans Learning systems Computational intelligence

来源：评论

学校读者我要写书评

暂无评论

Automatic image registration using virtual circles

引用

International Journal of Image and Graphics 2004年第2期4卷 281-299页

作者： Alhichri, Haikel S. Kamel, Mohamed Pattern Analysis and Machine Intelligence Laboratory Systems Design Engineering University of Waterloo 200 University Ave. West WaterlooONN2L3G1 Canada University of Waterloo Canada

The main contribution of this work is a novel set of image features called the virtual circles and their use in the registration of images under similarity transformations. A virtual circle is a circle with maximal radius encompassing a background area that does not contain edge points. It has many useful properties such as its radius, and its dominant edge direction for example, which can be utilized for efficient registration. Furthermore, virtual circles are frequent and can be extracted efficiently with the help of the distance transform from many types of images. We have tested the new virtual circles method in the registration of 66 pairs of images, half of which are printed labels and the other half are indoor scenes. Experimental results have shown that this method has a linear complexity in terms of the number of pixels. It is also highly automatic, because it has a small number of parameters, which almost never need to be changed throughout the experiments. © 2004 World Scientific Publishing Company.

关键词： Image registration

来源：评论

学校读者我要写书评

暂无评论

Shape retrieval using concavity trees

Shape retrieval using concavity trees

引用

International Conference on pattern Recognition

作者： O. El Badawy M. Kamel Pattern Analysis and Machine Intelligence Laboratory Systems Design Engineering University of Waterloo Waterloo ONT Canada

Concavity trees are well-known abstract structures. This paper proposes a new shape-based image retrieval method based on concavity trees. The proposed method has two main components. The first is an efficient (in terms of space and time) contour-based concavity tree extraction algorithm. The second component is a recursive concavity-tree matching algorithm that returns a distance between two trees. We demonstrate that concavity trees are able to boost the retrieval performance of two feature sets by at least 15% when tested on a database of 625 silhouette images.

关键词： Shape Image retrieval Information retrieval Testing Image databases pattern recognition pattern analysis machine intelligence Laboratories System analysis and design

来源：评论

学校读者我要写书评

暂无评论

Q(/spl Lambda/)-based image thresholding

Q(/spl Lambda/)-based image thresholding

引用

Canadian Conference on Computer and Robot Vision, CRV

作者： M. Shokri H.R. Tizhoosh Pattern Analysis and Machine Intelligence Lab Systems Design Engineering University of Waterloo ONT Canada

One of the problems in image processing is finding an appropriate threshold in order to convert an image to a binary one. In this paper we introduce a new method for image thresholding. We use reinforcement learning as an effective way to find the optimal threshold. Q(Λ) is implemented as a learning algorithm to achieve more accurate results. The reinforcement agent uses objective rewards to explore/exploit the solution space. It means that there is not any experienced operator involved and the reward and punishment function must be defined for the agent. The results show that this method works successfully and can be trained for any particular application.

关键词： Learning Histograms Image processing Image converters Image segmentation pattern analysis machine intelligence System analysis and design design engineering systems engineering and theory

来源：评论

学校读者我要写书评

暂无评论

A fuzzy set approach to extracting keywords from abstracts

A fuzzy set approach to extracting keywords from abstracts

引用

Conference of the North American Fuzzy Information Processing Society - NAFIPS

作者： M. Makrehchi M. Kamel Pattern Analysis and Machine Intelligence Lab Department of Systems Design Engineering University of Waterloo Waterloo ONT Canada Department of Systems Design Engineering University of Waterloo Waterloo Ontario Canada

An unsupervised keyword extraction method based on corpora is proposed. After representing each document in the collection by a fuzzy set of candidate keywords, the problem is translated into finding appropriate fuzzy membership degree for each candidate. In order to determine the membership degrees, first, all terms of the vocabulary are mapped into a two-dimensional space called class-collection map by obtaining two newly proposed fuzzy measures called fuzzy significance and fuzzy relevance for each term. At the second step, the mapped terms are grouped into three categories, namely, features, keywords and stopwords that are discriminated by their contribution to the meaning of the documents. Instead of a clustering approach for grouping purpose, a fuzzy rule base is provided. The method is independent of the language and data dimensionality. It does not require the use of dictionary, thesaurus nor natural language processing.

关键词： Fuzzy sets Vocabulary Web pages Abstracts Text mining Fuzzy systems pattern analysis machine intelligence System analysis and design design engineering

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：