检索结果-内蒙古大学图书馆

Enhancing Deep Neural Network Saliency Visualizations With Gradual Extrapolation

IEEE ACCESS 2021年 9卷 95155-95161页

作者： Szandala, Tomasz Wroclaw Univ Sci & Technol PL-50372 Wroclaw Poland

In this paper, an enhancement technique for the class activation mapping methods such as gradient-weighted class activation maps or excitation backpropagation is proposed to present the visual explanations of decisions from convolutional neural network-based models. The proposed idea, called Gradual Extrapolation, can supplement any method that generates a heatmap picture by sharpening the output. Instead of producing a coarse localization map that highlights the important predictive regions in the image, the proposed method outputs the specific shape that most contributes to the model output. Thus, the proposed method improves the accuracy of saliency maps. The effect has been achieved by the gradual propagation of the crude map obtained in the deep layer through all preceding layers with respect to their activations. In validation tests conducted on a selected set of images, the faithfulness, interpretability, and applicability of the method are evaluated. The proposed technique significantly improves the localization detection of the neural networks' attention at low additional computational costs. Furthermore, the proposed method is applicable to a variety deep neural network models. The code for the method can be found at https://***/szandala/gradual-extrapolation

关键词： Heating systems backpropagation Visualization Neural networks Ions Extrapolation Predictive models Deep neural networks backpropagation algorithms computer vision explainable artificial intelligence XAI visualization

来源：评论

学校读者我要写书评

暂无评论

Scanner color management model based on improved back-propagation neural network

引用

Chinese Optics Letters 2008年第3期6卷 231-234页

作者：黎新伍 Electronic Business Department of Jiangxi University of Finance and Economics

Scanner color management is one of the key techniques for color reproduction in information optics. A new scanner color management model is presented based on analyzing rendering principle of scanning objects. In this model, a standard color target is taken as experimental sample. Color blocks in color shade area are used to substitute complete color space to solve the difficulties in selecting experimental color blocks. Immune genetic algorithm is used to correct back-propagation neural network （BPNN） to speed up the convergence of the model. Experimental results show that the model can improve the accuracy of scanner color management.

关键词： backpropagation algorithms Genetic algorithms Neural networks Scanning

来源：评论

学校读者我要写书评

暂无评论

HIDDEN CONTROL NEURAL ARCHITECTURE MODELING OF NONLINEAR TIME-VARYING SYSTEMS AND ITS APPLICATIONS

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS 1993年第1期4卷 109-116页

作者： LEVIN, E Speech Research Department AT and T Bell Laboratories Inc. Murray Hill NJ USA

Multilayered neural networks have been proposed recently for nonlinear prediction and system modeling [1]-[6]. Although neural networks have *** for modeling time invariant nonlinear systems, it has been difficult to apply them to complicated nonstationary signals, such as speech because they are unable to characterize temporal variability. In this paper we address this problem by proposing a network architecture, called ''hidden control neural network'' (HCNN) [4], for modeling signals generated by nonlinear dynamical systems with restricted time variability. Our approach is to allow the mapping that is implemented by a multilayered neural network to change with time as a function of an additional control input signal. This network is trained using an algorithm that is based on ''back-propagation'' and segmentation algorithms for estimating the unknown control together with the network's parameters. This network wa$ applied to three different tasks: segmentation and modeling of a signal produced by a time-varying nonlinear system;speaker-independent recognition of spoken connected digit;and on-line recognition of handwritten characters. The results of these experiments demonstrate the ability of HCNN to learn time-varying nonlinear dynamics, and its potential for high performance recognition of signals, produced by time-varying sources, such as spoken utterances, and written characters.

关键词： Neural networks Time varying systems Character recognition Handwriting recognition Nonlinear systems Nonlinear dynamical systems backpropagation algorithms Speech Nonlinear control systems Signal generators

来源：评论

学校读者我要写书评

暂无评论

GRADIENT CALCULATIONS FOR DYNAMIC RECURRENT NEURAL NETWORKS - A SURVEY

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS 1995年第5期6卷 1212-1228页

作者： PEARLMUTTER, BA Learning Systems Department Siemens AG Corporate Research and Development Princeton NJ USA

We survey learning algorithms for recurrent neural networks with hidden units and put the various techniques into a common framework, We discuss fixed point learning algorithms, namely recurrent backpropagation and deterministic Boltzmann machines, and nonfixed point algorithms, namely backpropagation through time, Elman's history cutoff, and Jordan's output feedback architecture, Forward propagation, an on-line technique that uses adjoint equations, and variations thereof, are also discussed, In many cases, the unified presentation leads to generalizations of various sorts, We discuss advantages and disadvantages of temporally continuous neural networks in contrast to clocked ones continue with some ''tricks of the trade'' for training, using, and simulating continuous time and recurrent neural networks, We present some simulations, and at the end, address issues of computational complexity and learning speed.

关键词： Recurrent neural networks backpropagation algorithms Computational modeling Machine learning History Output feedback Equations Neural networks Clocks Computational complexity

来源：评论

学校读者我要写书评

暂无评论

Accelerating the training of feedforward neural networks using generalized Hebbian rules for initializing the internal representations

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS 1996年第2期7卷 419-426页

作者： Karayiannis, NB Department of Electrical and Computer Engineering University of Houston TX USA

This paper presents an unsupervised learning scheme for initializing the internal representations of feedforward neural networks, which accelerates the convergence of supervised learning algorithms. It is proposed in this paper that the initial set of internal representations can be formed through a bottom-up unsupervised learning process applied before the top-down supervised training algorithm. The synaptic weights that connect the input of the network with the hidden units can be determined through linear or nonlinear variations of a generalized Hebbian learning rule, known as Oja's rule. Various generalized Hebbian rules were experimentally tested and evaluated in terms of their effect on the convergence of the supervised training process. Several experiments indicated that the use of the proposed initialization of the internal representations significantly improves the convergence of gradient-descent-based algorithms used to perform nontrivial training tasks. The improvement of the convergence becomes significant as the size and complexity of the training task increase.

关键词： Acceleration Neural networks Feedforward neural networks backpropagation algorithms Convergence Application software Unsupervised learning Multi-layer neural network Entropy Supervised learning

来源：评论

学校读者我要写书评

暂无评论

MAXIMUM-LIKELIHOOD-ESTIMATION OF OBJECT LOCATION IN DIFFRACTION TOMOGRAPHY .2. STRONGLY SCATTERING OBJECTS

引用

IEEE TRANSACTIONS ON SIGNAL PROCESSING 1991年第6期39卷 1466-1470页

作者： TSIHRINTZIS, GA DEVANEY, AJ AJ DEVANEY ASSOCIATES INC BOSTONMA 02116

The problem of estimating the location of a known scattering object from noisy, limited scattering data is solved within exact, scalar wave scattering theory. The estimation procedure is shown to be a generalization of an earlier procedure [1], [2] developed within the Born and Rytov approximations of weak scattering theory and is compared with that earlier procedure in a computer simulation study.

关键词： Maximum likelihood estimation Diffraction Radar scattering Matched filters Computed tomography backpropagation algorithms Computer simulation Estimation theory Scattering parameters Parameter estimation

来源：评论

学校读者我要写书评

暂无评论

Improving the back-propagation algorithm using evolutionary strategy

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS 2007年第2期54卷 171-175页

作者： Siu, Sammy Yang, Sheng-Sung Lee, Chien-Min Ho, Chia-Lu Chunghwa Telecom Co Ltd Telecom Labs Tao Yuan 326 Taiwan Natl Cent Univ Inst Elect Engn Chungli 32054 Taiwan Ind Technol Res Inst Informat & Commun Res Labs New Mobile Access Dept Hsinchu 310 Taiwan Natl Cent Univ Inst Commun Engn Chungli 32054 Taiwan

In order to overcome the existence of the local minimum in the multilayer perceptron (MLP) implemented with back-propagation (BP) algorithm, the evolutionary strategy (ES) is proposed. Introducing the factors of the chromosome and gene mutation rates, one can enhance the flexibility of the mutation. The bounds of the chromosome and gene mutation rates are derived. Simulation results are shown to verify the theoretical calculations and also suggest appropriate strategy parameter values. The theoretical results are studied using the MLP-based decision feedback equalizer (MLP DFE) scenarios. The results indicate that the evolutionary strategy outperforms the BP algorithm.

关键词： Genetic mutations Biological cells backpropagation algorithms Multilayer perceptrons Decision feedback equalizers Telecommunications Robustness Laboratories Communication industry Mobile communication

来源：评论

学校读者我要写书评

暂无评论

The Pandemonium system of reflective agents

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS 1996年第1期7卷 97-106页

作者： Smieja, F Gesellscbaft für Mathematik und Datenverarbeitung Sankt Augustin Germany

The Pandemonium system of reflective MINOS agents solves problems by automatic dynamic modularization of the input space, The agents contain feedforward neural networks which adapt using the backpropagation algorithm, We demonstrate the performance of Pandemonium on various categories of problems, These include learning continuous functions with discontinuities, separating two spirals, learning the parity function, and optical character recognition, It is shown how strongly the advantages gained from using a modularization technique depend on the nature of the problem, The superiority of the Pandemonium method over a single net on the first two test categories is contrasted with its limited advantages for the second two categories, In the first case the system converges quicker with modularization and is seen to lead to simpler solutions, For the second case the problem is not significantly simplified through flat decomposition of the input space, although convergence is still quicker.

关键词： discontinuities Modularity backpropagation algorithms optical character recognition feedforward neural nets Agents Continuous Function

来源：评论

学校读者我要写书评

暂无评论

ADAPTIVE algorithms WITH NONLINEAR DATA AND ERROR FUNCTIONS

引用

IEEE TRANSACTIONS ON SIGNAL PROCESSING 1992年第9期40卷 2199-2206页

作者： SETHARES, WA Department of Electrical and Computer Engineering University of Wisconsin Madison Madison WI USA

Using the tools of nonlinear system theory, we examine several common nonlinear variants of the LMS algorithm and derive a persistence of excitation criteria for local exponential stability. The condition is tight when the inputs are periodic, and a generic counterexample is demonstrated which gives (local) instability for a large class of such nonlinear versions of LMS, specifically, those which utilize a nonlinear data function. The presence of a nonlinear error function is found to be relatively benign in that it does not affect the stability of the error system. Rather, it defines the cost function the algorithm tends to minimize. Specific examples include the dead zone modification, the cubed data nonlinearity, the cubed error nonlinearity, the signed regressor algorithm, and a single layer version of the backpropagation algorithm.

关键词： Adaptive algorithm Least squares approximation Cost function backpropagation algorithms Nonlinear systems Convergence Adaptive systems Stability criteria Signal generators

来源：评论

学校读者我要写书评

暂无评论

Design and application of fuzzy neural network systems optimized with hybrid algorithms

引用

TRANSACTIONS OF THE INSTITUTE OF MEASUREMENT AND CONTROL 2024年第15期46卷 3063-3070页

作者： Chen, Yang Liu, Jiahuan Zhou, Junge Liaoning Univ Technol Coll Sci Jinzhou 121000 Peoples R China

Fuzzy neural network systems (FNNSs) can incorporate the merits of fuzzy logic systems (FLSs) and neural networks (NN). This paper designs a type of non-singleton FNNSs for forecasting issues. The proposed hybrid backpropagation (BP) algorithms and recursive least square (RLS) algorithms are used for optimizing the parameters of antecedents, input measurements, and consequents simultaneously. Two computer simulation examples based on the data of European Network on Intelligent Technology (EUNITE) and data of west Texas intermediate (WTI) crude oil price are used for testing. Convergence analysis shows that the hybrid optimized FNNSs have very high generalization ability.

关键词： Fuzzy neural network systems backpropagation algorithms recursive least square algorithms Gaussian type membership function generalization ability

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：