Use of Top-Down Information for Visual Information Processing
使用自上而下的信息进行视觉信息处理
基本信息
- 批准号:14380169
- 负责人:
- 金额:$ 8.7万
- 依托单位:
- 依托单位国家:日本
- 项目类别:Grant-in-Aid for Scientific Research (B)
- 财政年份:2002
- 资助国家:日本
- 起止时间:2002 至 2005
- 项目状态:已结题
- 来源:
- 关键词:
项目摘要
When we are looking at an object, we do not passively accept whole information within our visual field, but actively gather necessary information only. We focus our attention to the places that attract our interest. We capture information from there and process it selectively. We often try to predict a pattern using information from surrounding areas, and recognize it by confirming whether the initial prediction was correct. Top-down information plays an important role for such active processing of information.Varieties of neurophysiological and psychological experimental results on higher brain functions, including top-down processing, have recently been reported. We tried to analyze these results systematically from the stand-point of information processing, and made modeling research to obtain new design principles for information processors of a new generation. Namely, we first propose a new model for a higher brain function, and improved the model so as to behave in a similar way as the biological brain. At the same time, we also made several experiments for practical implementation of the models to real-world problems.As a result of these researches, we have obtained the following results :(1)A model capable of recognizing and restoring partly occluded patterns(2)Improving the recognition rate of the neocognitron (a model for robust visual pattern recognition)(3)A new method for incremental learning appropriate for multi-layered neural network(4)Use of blur for robust image processing --- a neural network model that extracts axes of symmetry from visual patterns(5)Extraction of optic flow : A model of neural network for MT and MST cells(6)Psychological experiments and models revealing relations among the mechanisms of figure-ground separation, contour integration, and motion integration.(7)Relations among the perception for LPD stimuli, global motion integration, and transparent motion : psychological experiments and a computational model
当我们看一个物体时,我们不是被动地接受视野内的全部信息,而是主动地只收集必要的信息。我们把注意力集中在吸引我们兴趣的地方。我们从那里获取信息并有选择地处理它。我们经常尝试使用周围区域的信息来预测模式,并通过确认最初的预测是否正确来识别它。自上而下的信息在这种主动的信息加工过程中起着重要的作用,包括自上而下加工在内的各种神经生理学和心理学的高级脑功能的实验结果最近被报道。我们试图从信息处理的角度对这些结果进行系统的分析,并进行建模研究,以获得新一代信息处理器的新设计原则。也就是说,我们首先提出了一个新的模型,为更高的大脑功能,并改进了模型,以便表现出类似的方式作为生物大脑。同时,我们还对模型在实际问题中的应用进行了实验研究,取得了以下成果:(1)建立了一个能够识别和恢复部分遮挡模式的模型;(2)提高了新认知机的识别率(用于鲁棒视觉模式识别的模型)(3)适合于多层神经网络的增量学习的新方法(4)用于鲁棒图像处理的模糊的使用-从视觉模式提取对称轴的神经网络模型(5)光流的提取:MT和MST细胞的神经网络模型(6)揭示图形-背景分离、轮廓整合和运动整合机制之间关系的心理学实验和模型。(7)对LPD刺激的感知、整体运动整合和透明运动之间的关系:心理学实验和计算模型
项目成果
期刊论文数量(42)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
Modeling Neural Networks for Artificial Vision
人工视觉神经网络建模
- DOI:
- 发表时间:2006
- 期刊:
- 影响因子:0
- 作者:遠山和也;福島邦彦;K.Fukushima
- 通讯作者:K.Fukushima
K.Fukushima: "Restoring partly occluded patterns : a neural network model with backward paths"Artificial Neural Networks and Neural Information Processing---ICANN/ICONIP 2003. 393-400 (2003)
K.Fukushima:“恢复部分遮挡的模式:具有后向路径的神经网络模型”人工神经网络和神经信息处理---ICANN/ICONIP 2003. 393-400 (2003)
- DOI:
- 发表时间:
- 期刊:
- 影响因子:0
- 作者:
- 通讯作者:
K.Fnkushima: "Neocognitron for handwritten digit recognition"Neurocomputing. (印刷中). (2003)
K.Fnkushima:“用于手写数字识别的 Neocognitron”神经计算(出版中)。
- DOI:
- 发表时间:
- 期刊:
- 影响因子:0
- 作者:
- 通讯作者:
Neural network model restoring partly occluded patterns
恢复部分遮挡模式的神经网络模型
- DOI:
- 发表时间:2004
- 期刊:
- 影响因子:0
- 作者:O.Watanabe;M.Kikuchi;K.Fukushima;K.Fukushima
- 通讯作者:K.Fukushima
Local and global motion integration mechanisms in human visual system are independent
人类视觉系统中的局部和全局运动整合机制是独立的
- DOI:
- 发表时间:2004
- 期刊:
- 影响因子:0
- 作者:O.Watanabe;M.Kikuchi
- 通讯作者:M.Kikuchi
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
数据更新时间:{{ journalArticles.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ monograph.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ sciAawards.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ conferencePapers.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ patent.updateTime }}
FUKUSHIMA Kunihiko其他文献
FUKUSHIMA Kunihiko的其他文献
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
{{ truncateString('FUKUSHIMA Kunihiko', 18)}}的其他基金
Dynamic Processing of Visual Patterns
视觉模式的动态处理
- 批准号:
09308010 - 财政年份:1997
- 资助金额:
$ 8.7万 - 项目类别:
Grant-in-Aid for Scientific Research (A).
Research on Visual Pattern Recognition with Hierarchical Neural Networks
层次神经网络视觉模式识别研究
- 批准号:
07408005 - 财政年份:1995
- 资助金额:
$ 8.7万 - 项目类别:
Grant-in-Aid for Scientific Research (A)
Research on Visual Pattern Recognition with Hierarchical Neural Networks
层次神经网络视觉模式识别研究
- 批准号:
02402035 - 财政年份:1990
- 资助金额:
$ 8.7万 - 项目类别:
Grant-in-Aid for General Scientific Research (A)
相似海外基金
Collaborative Research: Frameworks: Diamond: Democratizing Large Neural Network Model Training for Science
合作研究:框架:钻石:科学大型神经网络模型训练的民主化
- 批准号:
2311766 - 财政年份:2023
- 资助金额:
$ 8.7万 - 项目类别:
Standard Grant
Collaborative Research: Frameworks: Diamond: Democratizing Large Neural Network Model Training for Science
合作研究:框架:钻石:科学大型神经网络模型训练的民主化
- 批准号:
2311769 - 财政年份:2023
- 资助金额:
$ 8.7万 - 项目类别:
Standard Grant
Collaborative Research: Frameworks: Diamond: Democratizing Large Neural Network Model Training for Science
合作研究:框架:钻石:科学大型神经网络模型训练的民主化
- 批准号:
2311768 - 财政年份:2023
- 资助金额:
$ 8.7万 - 项目类别:
Standard Grant
Collaborative Research: Frameworks: Diamond: Democratizing Large Neural Network Model Training for Science
合作研究:框架:钻石:科学大型神经网络模型训练的民主化
- 批准号:
2311767 - 财政年份:2023
- 资助金额:
$ 8.7万 - 项目类别:
Standard Grant
Collaborative Research: Frameworks: Diamond: Democratizing Large Neural Network Model Training for Science
合作研究:框架:钻石:科学大型神经网络模型训练的民主化
- 批准号:
2401245 - 财政年份:2023
- 资助金额:
$ 8.7万 - 项目类别:
Standard Grant
A physics-driven neural network model of working memory
物理驱动的工作记忆神经网络模型
- 批准号:
570263-2022 - 财政年份:2022
- 资助金额:
$ 8.7万 - 项目类别:
Alexander Graham Bell Canada Graduate Scholarships - Doctoral
An artificial neural network model of the exploration-exploitation trade off
探索-利用权衡的人工神经网络模型
- 批准号:
559572-2021 - 财政年份:2022
- 资助金额:
$ 8.7万 - 项目类别:
Postgraduate Scholarships - Doctoral
Testing a deep-neural network model of cognitive map development
测试认知图开发的深度神经网络模型
- 批准号:
2725859 - 财政年份:2022
- 资助金额:
$ 8.7万 - 项目类别:
Studentship
Graph Neural Network model for prediction of treatment response in DLBCL
用于预测 DLBCL 治疗反应的图神经网络模型
- 批准号:
563543-2021 - 财政年份:2021
- 资助金额:
$ 8.7万 - 项目类别:
University Undergraduate Student Research Awards
EAGER: CAS-Climate: AI-driven Probabilistic Technique, Quantile Regression based Artificial Neural Network Model, for Bias Correction and Downscaling of CMIP6 Projections
EAGER:CAS-Climate:人工智能驱动的概率技术、基于分位数回归的人工神经网络模型,用于 CMIP6 投影的偏差校正和缩小
- 批准号:
2151651 - 财政年份:2021
- 资助金额:
$ 8.7万 - 项目类别:
Standard Grant














{{item.name}}会员




