检索结果-内蒙古大学图书馆

conference on applications of artificial neural networks in image processing Vii

作者： Hu, CLJ So Illinois Univ Dept Elect & Comp Engn Carbondale IL 62901 USA

ISBN: (纸本)081944815X

A feedback neural network (FBNN) can be triggered by ANY input analog pattern vector. Then depending on the domain-of-convergence (or domain-of-attraction in the languages of nonlinear systems) that this triggering pattern falls into, the FBNN will go around and around the feedback loop and finally settle down at one of the few designated patterns associatively stored in the connection matrix. This recalled (or the settle-down) pattern will stay at the output even when the input triggering pattern is removed because of the self-sustained feedback action of the FBNN. The triggering pattern does not have to be the same as the stored pattern that it recalls. It can be a noise-affected pattern. But as long as it falls within the designated noise range (or the designated domain of convergence) of an accurately stored pattern, that accurate pattern will be recalled and permanently appear at the output even when the input triggering is removed.

关键词： feedback neural networks associative pattern storage noise-affected recalls of accurate patterns

来源：评论

学校读者我要写书评

暂无评论

artificial Intelligence applications and Innovations 2012

引用

丛书名： IFIP Advances in Information and Communication Technology

2012年

作者： Lazaros S. Iliadis Ilias Maglogiannis Harris Papadopoulos

ISBN: (数字)9783642334092

ISBN: (纸本)9783642334085

This book constitutes the refereed proceedings of the 8th IFIP WG 12.5 International conference on artificial Intelligence applications and Innovations, AIAI 2012, held in Halkidiki, Greece, in September 2012. The 44 revised full papers and 5 revised short papers presented were carefully reviewed and selected from 98 submissions. The papers are organized in topical sections on ANN-classification and pattern recognition, optimization - genetic algorithms, artificial neural networks, learning and mining, fuzzy logic, classification - pattern recognition, multi-agent systems, multi-attribute DSS, clustering, image-video classification and processing, and engineering applications of AI and artificial neural networks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Character recognition by synergetic neural network based on selective attention parameters

Character recognition by synergetic neural network based on ...

引用

conference on applications of artificial neural networks in image processing Vii

作者： Wang, MX Mo, YL Ma, JL Shanghai Univ Dept Commun Engn Shanghai 200072 Peoples R China

ISBN: (纸本)081944815X

In this paper a learning algorithm of synergetic neural network based on selective attention parameters is proposed. According to the mechanism of the Human Visual System (HVS), the weight matrix of synergetic neural network can be obtained by multiplying the prototype matrix by selective attention parameters. Two selective attention models based on the human visual system are put forward in this paper. The comparative experiments between the traditional algorithm SCAP and the new method we proposed in the application of recognising the real gray images of numeric and alphabetic characters are done. And the results show that our method can improve the synergetic neural network's recognition performance and be more suitable to human visual system.

关键词： character recognition synergetic neural network human visual system selective attention parameters

来源：评论

学校读者我要写书评

暂无评论

A Comparison of Activation Functions in artificial neural networks 26

A Comparison of Activation Functions in Artificial Neural Ne...

引用

26th IEEE Signal processing and Communications applications conference (SIU)

作者： Bircanoglu, Cenk Arica, Nafiz Bahcesehir Univ Bilgisayar Muhendisligi Bolumu Istanbul Turkey

ISBN: (纸本)9781538615010

In this study, the effects of Activation Functions (AF) in artificial neural Network (ANN) on regression and classification performance are compared. In comparisons, success rates in test data and duration of training are evaluated for both problems. A total of 11 AF functions, 10 AF commonly used in the literature and Square function proposed in this study, are compared using 7 different datasets, 2 for regression and 5 for classification. 3 different ANN architectures, which are considered to be the most appropriate for each dataset are employed in the experiments. As a result of totally 231 different training procedures, the effects of Afs are examined for different datasets and architectures. Similarly, the effects of AF on training time are shown for different datasets. In the experiments it is shown that ReLU is the most succesfull AF in general purposes. In addition to ReLU, Square function gives the better results in image datasets.

关键词： activation function deep learning regression classification artificial neural networks

来源：评论

学校读者我要写书评

暂无评论

LEARNING TO DISTINGUISH SIMILAR OBJECTS

LEARNING TO DISTINGUISH SIMILAR OBJECTS

引用

1st International conference on applications and Science of artificial neural networks

作者： SEIBERT, M WAXMAN, A GOVE, A MIT LINCOLN LABMACHINE INTELLIGENCE TECHNOL GRPLEXINGTONMA 02173

ISBN: (纸本)0819418455

This paper describes how the similarities and differences among similar objects can be discovered during learning to facilitate recognition. The application domain is single views of flying model aircraft captured in silhouette by a CCD camera. The approach was motivated by human psychovisual and monkey neurophysiological data. The implementation uses neural net processing mechanisms to build a hierarchy that relates similar objects to superordinate classes, while simultaneously discovering the salient differences between objects within a class. Learning and recognition experiments both with and without the class similarity and difference learning show the effectiveness of the approach on this visual data. To test the approach, the hierarchical approach was compared to a non-hierarchical approach, and was found to improve the average percentage of correctly classified views from 77% to 84%.

关键词： Optical spheres Tin image processing image segmentation Visualization Composites CCD cameras Feature extraction neural networks Sensors

来源：评论

学校读者我要写书评

暂无评论

Real-time camera-based face detection using a modified LAMSTAR neural network system

Real-time camera-based face detection using a modified LAMST...

引用

conference on applications of artificial neural networks in image processing Vii

作者： Girado, JI Sandin, DJ DeFanti, TA Wolf, LK Univ Illinois Elect Visualizat Lab Chicago IL 60607 USA

ISBN: (纸本)081944815X

This paper describes a cost-effective, real-time (640x480 at 30Hz) upright frontal face detector as part of an ongoing project to develop a video-based, tetherless 3D head position and orientation tracking system. The work is specifically targeted for auto-stereoscopic displays and projection-based virtual reality systems. The proposed face detector is based on a modified LAMSTAR neural network system. At the input stage, after achieving image normalization and equalization, a sub-window analyzes facial features using a neural network. The sub-window is segmented, and each part is fed to a neural network layer consisting of a Kohonen Self-Organizing Map (SOM). The output of the SOM neural networks are interconnected and related by correlation-links, and can hence determine the presence of a face with enough redundancy to provide a high detection rate. To avoid tracking multiple faces simultaneously, the system is initially trained to track only the face centered in a box superimposed on the display. The system is also rotationally and size invariant to a certain degree.

关键词： face tracking face detection artificial neural networks LAMSTAR head tracking

来源：评论

学校读者我要写书评

暂无评论

Generative Models for Fashion Industry using Deep neural networks 2

Generative Models for Fashion Industry using Deep Neural Net...

引用

2nd International conference on Computer applications and Information Security (ICCAIS)

作者： Lomov, Ildar Makarov, Ilya Natl Res Univ Higher Sch Econ Sch Data Anal & Artificial Intelligence 3 Kochnovskiy Proezd Moscow 125319 Russia

ISBN: (纸本)9781728101088

The progress of deep learning models in image and video processing leads to new artificial intelligence applications in Fashion industry. We consider the application of Generative Adversarial networks and neural Style Transfer for Digital Fashion presented as Virtual fashion for trying new clothes. Our model generate humans in clothes with respect to different fashion preferences, color layouts and fashion style. We propose that the virtual fashion industry will be highly impacted by accuracy of generating personalized human model taking into account different aspects of product and human preferences. We compare our model with state-of-art VITON model and show that using new perceptual loss in deep neural network architecture lead to better qualitative results in generating humans in clothes.

关键词： Generative Adversarial networks neural Style Transfer image Generation Human Model Generation Design Methodology artificial Intelligence for Fashion Computational Design

来源：评论

学校读者我要写书评

暂无评论

neural networks for image Recognition in Mobile applications 28

Neural Networks for Image Recognition in Mobile Applications

引用

28th International conference on Software, Telecommunications and Computer networks (SoftCOM)

作者： Zbiec, Izabela Poniszewska-Maranda, Aneta Krym, Tomasz Lodz Univ Technol Inst Informat Technol Lodz Poland

ISBN: (纸本)9789532900996

The image recognition and pattern recognition on a mobile platform are getting more and more popular. Many of libraries and tools were created to make implementing new solutions easier. The goal of the paper was to present the analysis of selected machine learning algorithms for image recognition in mobile applications on the Android platform on the example of application that recognises the chosen images - tree leafs. The MLP (multilayer perceptron) artificial neural network was used as a tool to classify the objects. The program was implemented and trained in Python. The important part of the research was the image pre-processing: many of popular algorithms were tested, for example a mean filter or a Canny's edges detector. The final result was the mobile solution that uses the learned model of MLP neural network to recognize a leaf on the photo.

关键词： image recognition neural networks mobile applications Android system TensorFlow library

来源：评论

学校读者我要写书评

暂无评论

Novelty Detection in Time Series Using Self-Organizing neural networks: A Comprehensive Evaluation

引用

neural processing LETTERS 2018年第2期47卷 717-744页

作者： Aguayo, Leonardo Barreto, Guilherme A. Univ Brasilia Dept Elect Engn Brasilia DF Brazil Fed Univ Ceara UFC Dept Teleinformat Engn Fortaleza Ceara Brazil

In this survey paper, we report the results of a comprehensive study involving the application of dynamic self-organizing neural networks (SONNs) to the problem of novelty detection in time series data. The study is comprised of three main parts. In the first part, we aim at evaluating how the performances of nonrecurrent dynamic SONNs are influenced by the introduction of different short-term memory kernels, such as Gamma, Gamma ii and Laguerre, in the network input. In the second part, we analyze the performances of recurrent dynamic SONNs with the goal of inferring if they possess or not any competitive advantage over nonrecurrent architectures for novelty detection in time series. Finally, in the third part of the study, we introduce an alternative approach for dynamic SONN-based novelty detection by revisiting the operator map framework introduced by Lampinen and Oja (Proceedings of the 6th Scandinavian conference on image analysis (SCIA'89), pp 120-127, 1989) and Lehtimaki et al. (Proceedings of the joint international conference on artificial neural networks and neural information processing (ICANN/ICONIP'2003), pp 622-629, 2003). This framework allows the design of dynamic SONNs whose neurons are regarded as adaptive local linear models. In this case, novel/abnormal patterns are detected based on the statistics of prediction errors of the local models. A comprehensive performance comparison involving several nonrecurrent and recurrent dynamic SONN architectures is carried out using both synthetic and real-world time series data.

关键词： Time series modeling Novelty detection Self-organizing maps Quantization error Adaptive filtering Prediction error

来源：评论

学校读者我要写书评

暂无评论

A computational intelligence system for cell classification 2

A computational intelligence system for cell classification

引用

1998 IEEE International conference on Information Technology applications in Biomedicine (ITAB 98)

作者： Lin, W Xiao, JH Micheli-Tzanakou, E Rutgers State Univ Dept Biomed Engn Piscataway NJ 08855 USA

ISBN: (纸本)0780349733

artificial neural networks mere used to classify blood cells. Compared with existing methods, neural networks are more accurate, efficient, adaptable and information-rich. The implementation of the system in a PC/Windows NT environment using image processing technology and database management allows for a variety of features to be extracted and a variety of training algorithms to be used. In this preliminary study, blood cell images are segmented to individual cells. Features for individual cells, including size, color content and shape-related moments, are extracted and used as inputs to a multi-layer neural network. Backpropagation and ALOPEX training algorithms were used to train the neural network. After less than 2000 training iterations using 95 training sets, the system recognized three kinds of blood cell in a correctness percentage of 100%. This module provides a platform to build a more sophisticated computational intelligent system for cell classification for clinical use.

关键词： artificial neural networks cell classification features image processing

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：