检索结果-内蒙古大学图书馆

34th International Symposium on Multiple-Valued Logic (ISMVL 2004)

作者： Ngom, A Simovici, DA Stojmenovic, I Univ Windsor Dept Comp Sci Windsor ON N9B 3P4 Canada

ISBN: (纸本)0769521304

We consider the problem of synthesizing multiple-valued logic functions by neural networks. An evolutionary strategy (ES) which finds the longest strip in V subset of or equal to K-n is described. A strip contains points located between two parallel hyperplanes. Repeated application of ES partitions the space V into certain number of strips, each of them corresponding to a hidden unit. We construct neural networks based on these hidden units. Preliminary experimental results are presented and discussed.

关键词： multiple-valued logic multiple-threshold perceptron evolution strategy neural network partitioning method constructive algorithm

来源：评论

学校读者我要写书评

暂无评论

Should I Stay or Should I Grow? A Dynamic Self-Governed Growth for Determining Hidden Layer Size in a Multilayer Perceptron

Should I Stay or Should I Grow? A Dynamic Self-Governed Grow...

引用

International Joint Conference on Neural Networks (IJCNN) held as part of the IEEE World Congress on Computational Intelligence (IEEE WCCI)

作者： Ross, Matt Berberian, Nareg Chartier, Sylvain Univ Ottawa Sch Psychol Ottawa ON Canada

ISBN: (纸本)9781728169262

A novel dynamic self-governed growth algorithm inspired from population dynamics is introduced in a Multi-Layer Perceptron (MLP). This allows the inclusion of a carrying capacity, which is the maximum population of hidden units that can be sustained in a single hidden layer. The inclusion of this constraint in combination with population dynamics provides a built-in mechanism for a dynamic growth rate. The proposed approach is used in parallel with direct performance feedback from the network to modulate the growth rate of the hidden layer. This algorithm incrementally adds units to the hidden layer up to a point where the complexity of the task no longer requires further addition. The MLP is extended with the growing algorithm and its adaptability is tested by subjecting the network to increasing levels of task complexity for the n-bit problem. Using fixed rules that dictate both the size of a fixed layer MLP (fMLP) and the upper bound carrying capacity of the growing MLP (gMLP), the resulting topologies are directly compared for the n-bit problem. In short, the results suggest that even if an upper boundary of the carrying capacity is set by a fixed rule, the growing algorithm is capable of converging to less than the predicted number of units required for solving the given task. With the majority of trials growing to the same number of hidden units regardless of the rule used. This effect is consistent across the specified rules and levels of task complexity for the n-bit problem.

关键词： multilayer perceptron growing constructive algorithm population dynamics artificial neural networks parity n-bit

来源：评论

学校读者我要写书评

暂无评论

Dynamic Pick-Up and Delivery Optimization With Multiple Dynamic Events in Real-World Environment

引用

IEEE ACCESS 2019年 7卷 146209-146220页

作者： Sun, Baofeng Yang, Yue Shi, Junyan Zheng, Lili Jilin Univ Coll Transportat Changchun 130025 Jilin Peoples R China

Real-time city distribution strategies are highly dependent on dynamic environments, requiring timely responses to real-time changes due to various dynamic events that take place in the distribution system. Considering the influence of four kinds of real-time information on vehicle routing and vehicle scheduling, including new requests arriving gradually, old requests being modified or canceled, traffic congestion and vehicle breakdowns, a dynamic vehicle routing model based on a dynamic pick-up and delivery problem considering multiple dynamic events in a real-world environment (DPDP-MDE) is established. A dynamic algorithm framework is designed to solve the problem, the tabu search (TS) algorithm and the adaptive large neighborhood search (ALNS) algorithm are adopted to improve the quality of the initial solution, and the dynamic insertion method is adopted to solve the synchronization problem of unfixed requests (that is, unaccepted customer requests and modified requests) and new requests. The experimental results show that the model and dynamic algorithm framework proposed in this paper can effectively solve the dynamic pick-up and delivery problem with time windows (DPDP-TW). At different scheduling time horizons T, the TS algorithm improves the initial solution by an average of 3.11% and the ALNS algorithm by an average of 9.98%. Under different degrees of urgency, compared to the ALNS algorithm, the quality of the solution produced by the TS algorithm is not high, but the computation time is very small and it is relatively stable. Under different request sizes, the TS algorithm can obtain optimization results in 60s under four request levels, which gives it a significant advantage over the ALNS algorithm.

关键词： Dynamic pick-up and delivery problem dynamic events dynamic algorithm framework constructive algorithm tabu search algorithms adaptive large neighborhood search algorithms

来源：评论

学校读者我要写书评

暂无评论

Evolutionary strategy for learning multiple-valued logic functions

引用

JOURNAL OF MULTIPLE-VALUED LOGIC AND SOFT COMPUTING 2006年第5-6期12卷 459-489页

作者： Ngom, Alioune Simovici, Dan A. Stojmenovic, Ivan Univ Windsor Dept Comp Sci Windsor ON N9B 3P4 Canada Univ Massachusetts Dept Math & Comp Sci Boston MA 02125 USA Univ Ottawa Sch Informat Technol & Engn Dept Comp Sci Ottawa ON K1N 6N5 Canada

We consider the problem of synthesizing multiple-valued logic functions by neural networks. An evolutionary strategy (ES) which finds the longest strip in V subset of K-n is described. A strip contains points located between two parallel hyperplanes. Repeated application of ES partitions the space V into certain number of strips, each of them corresponding to a hidden unit. We construct neural networks based on these hidden units. Preliminary experimental results are presented and discussed.

关键词： multiple-valued logic multiple-threshold perceptron evolution strategy neural network partitioning method constructive algorithm

来源：评论

学校读者我要写书评

暂无评论

STRIP - A strip-based neural-network growth algorithm for learning multiple-valued functions

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS 2001年第2期12卷 212-227页

作者： Ngom, A Stojmenovic, I Milutinovic, V Univ Windsor Dept Comp Sci Windsor ON N9B 3P4 Canada Univ Ottawa Sch Informat Technol & Engn Dept Comp Sci Ottawa ON K1N 6N5 Canada Univ Belgrade Sch Elect Engn Dept Comp Engn YU-11120 Belgrade Serbia Yugoslavia

We consider the problem of synthesizing multipIe-valued logic functions by neural networks. A genetic algorithm (GA) which finds the longest strip in V subset of or equal to K (n) is described. A strip contains points located between two parallel hyperplanes. Repeated application of GA partitions the space V into certain number of strips, each of them corresponding to a hidden unit. We construct two neural networks based on these hidden units and show that they correctly compute the given but arbitrary multiple-valued function. Preliminary experimental results are presented and discussed.

关键词： constructive algorithm genetic algorithm multiple-threshold perceptron multiple-valued logic neural network partitioning

来源：评论

学校读者我要写书评

暂无评论

constructive APPROACHES FOR TRAINING OF WAVELET NEURAL NETWORKS USING ADAPTIVE LEARNING RATE

引用

INTERNATIONAL JOURNAL OF WAVELETS MULTIRESOLUTION AND INFORMATION PROCESSING 2013年第3期11卷 1350021-1350021页

作者： Skhiri, Mohamed Zine El Abidine Chtourou, Mohamed Univ Sfax Natl Sch Engn Sfax Dept Elect Engn Sfax Tunisia

This paper investigates the applicability of the constructive approach proposed in Ref. 1 to wavelet neural networks (WNN). In fact, two incremental training algorithms will be presented. The first one, known as one pattern at a time (OPAT) approach, is the WNN version of the method applied in Ref. 1. The second approach however proposes a modified version of Ref. 1, known as one epoch at a time (OEAT) approach. In the OPAT approach, the input patterns are trained incrementally one by one until all patterns are presented. If the algorithm gets stuck in a local minimum and could not escape after a fixed number of successive attempts, then a new wavelet called also wavelon, will be recruited. In the OEAT approach however, all the input patterns are presented one epoch at a time. During one epoch, each pattern is trained only once until all patterns are trained. If the resulting overall error is reduced, then all the patterns will be retrained for one more epoch. Otherwise, a new wavelon will be recruited. To guarantee the convergence of the trained networks, an adaptive learning rate has been introduced using the discrete Lyapunov stability theorem.

关键词： Wavelet neural networks constructive algorithm stability

来源：评论

学校读者我要写书评

暂无评论

Serial electrocardiography to detect newly emerging or aggravating cardiac pathology: a deep-learning approach

引用

BIOMEDICAL ENGINEERING ONLINE 2019年第1期18卷 15-15页

作者： Sbrollini, Agnese De Jongh, Marjolein C. Ter Haar, C. Cato Treskes, Roderick W. Man, Sumche Burattini, Laura Swenne, Cees A. Leiden Univ Med Ctr Cardiol Dept POB 9600 NL-2300 RC Leiden Netherlands Univ Politecn Marche Informat Engn Dept Via Brecce Bianche 12 I-60121 Ancona Italy

Background: Serial electrocardiography aims to contribute to electrocardiogram (ECG) diagnosis by comparing the ECG under consideration with a previously made ECG in the same individual. Here, we present a novel algorithm to construct dedicated deep-learning neural networks (NNs) that are specialized in detecting newly emerging or aggravating existing cardiac pathology in serial ECGs. Methods: We developed a novel deep-learning method for serial ECG analysis and tested its performance in detection of heart failure in post-infarction patients, and in the detection of ischemia in patients who underwent elective percutaneous coronary intervention. Core of the method is the repeated structuring and learning procedure that, when fed with 13 serial ECG difference features (intra-individual differences in: QRS duration;QT interval;QRS maximum;T-wave maximum;QRS integral;T-wave integral;QRS complexity;T-wave complexity;ventricular gradient;QRS-T spatial angle;heart rate;J-point amplitude;and T-wave symmetry), dynamically creates a NN of at most three hidden layers. An optimization process reduces the possibility of obtaining an inefficient NN due to adverse initialization. Results: Application of our method to the two clinical ECG databases yielded 3-layer NN architectures, both showing high testing performances (areas under the receiver operating curves were 84% and 83%, respectively). Conclusions: Our method was successful in two different clinical serial ECG applications. Further studies will investigate if other problem-specific NNs can successfully be constructed, and even if it will be possible to construct a universal NN to detect any pathologic ECG change.

关键词： Serial electrocardiography Vectorcardiography Deep learning Neural networks constructive algorithm

来源：评论

学校读者我要写书评

暂无评论

Inverse Density as an Inverse Problem: the Fredholm Equation Approach 13

Inverse Density as an Inverse Problem: the Fredholm Equation...

引用

Annual Conference on Neural Information Processing Systems

作者： Qichao Que Mikhail Belkin Department of Computer Science and Engineering The Ohio State University

ISBN: (纸本)9781632660244

We address the problem of estimating the ratio q/p where p is a density function and q is another density, or, more generally an arbitrary function. Knowing or approximating this ratio is needed in various problems of inference and integration often referred to as importance sampling in statistical inference. It is also closely related to the problem of covariate shift in transfer learning. Our approach is based on reformulating the problem of estimating the ratio as an inverse problem in terms of an integral operator corresponding to a kernel, known as the Fredholm problem of the first kind. This formulation, combined with the techniques of reg-ularization leads to a principled framework for constructing algorithms and for analyzing them theoretically. The resulting family of algorithms (FIRE, for Fredholm Inverse Regularized Estimator) is flexible, simple and easy to implement. We provide detailed theoretical analysis including concentration bounds and convergence rates for the Gaussian kernel for densities defined on R~d and smooth d-dimensional sub-manifolds of the Euclidean space. Model selection for unsupervised or semi-supervised inference is generally a difficult problem. It turns out that in the density ratio estimation setting, when samples from both distributions are available, simple completely unsupervised model selection methods are available. We call this mechanism CD-CV for Cross-Density Cross-Validation. We show encouraging experimental results including applications to classification within the covariate shift framework.

关键词： Inverse method Density functions Fredholm equations Transfer (Psychology) Statistical inference Seeds importance sampling Theoretical analysis model selection Inverse integration constructive algorithm

来源：评论

学校读者我要写书评

暂无评论

An Efficient Construction algorithm for Binary Interval Tree Nodes

An Efficient Construction Algorithm for Binary Interval Tree...

引用

2010 International Conference on Audio,Language and Image Processing(2010年音频、语言与图像处理国际会议 ICALIP 2010)

作者： Pan Wang Si-kun Li Xun Cai Liang Zeng School of Computer Science and Technology National University of Defense Technology Hunan Changsha 410073 China

ISBN: (纸本)9781424458653

The preprocessing almost take half of the whole time in isosurface extraction of large-scale data, thus it will make sense to shorten the preprocessing time to improve visualization efficiency. We develop a new construction algorithm for binary interval tree nodes based on partitioning span space, and it reduce the sorting computation considerably in isosurface extraction preprocessing. Both complexity analysis and experiments demonstrate the effectiveness of our new technique, and it has 50％ around performance promotion in our test data sets. So the new algorithm is practical in large-scale data isosurface extraction, especially for the real-time visualization system.

关键词： constructive algorithm tree nodes Isosurfaces New constructions Pretreatment new technique observational data Binary Complexity Analysis

来源：评论

学校读者我要写书评

暂无评论

Layered_CasPer: Layered cascade artificial neural networks

Layered_CasPer: Layered cascade artificial neural networks

引用

International Joint Conference on Neural Networks

作者： Tengfei Shen Dingyun Zhu Research School of Computer Science College of Engineering and Computer Science The Australian National University

ISBN: (纸本)9781467314886

Previous research has demonstrated that constructive algorithms are powerful methods for training feedforward neural networks. The CasPer algorithm is a constructive neural network algorithm that generates networks from a simple architecture and then expands it. The A_CasPer algorithm is a modified version of the CasPer algorithm which uses a candidate pool instead of a single neuron being trained. This research adds an extension to the A_CasPer algorithm in terms of the network architecture - the Layered_CasPer algorithm. The hidden neurons form as layers in the new version of the network structure which results in less computational cost being required. Beyond the network structure, other aspects of Layered_CasPer are the same as A_CasPer. The Layered_CasPer algorithm extension is benchmarked on a number of classification problems and compared to other constructive algorithms, which are CasCor, CasPer, A_CasPer, and AT_CasPer. It is shown that Layered_CasPer has a better performance on the datasets which have a large number of inputs for classification tasks. The Layered_CasPer algorithm has an advantage over other cascade style constructive algorithms in being more similar in topology to the familiar layered structure of traditional feedforward neural networks.

关键词： Cascade constructive algorithms Feedforward neural network CasPer A_CasPer CasCor AT_CasPer Layered_CasPer feedforward neural nets NETWORK STRUCTURE Artificial neural networks algorithms constructivity cascades Dataset constructive algorithm topology

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：