Optimum Training Schemes for Recurrent Neural Network Nonlinear Filters
循环神经网络非线性滤波器的最优训练方案
基本信息
- 批准号:9616391
- 负责人:
- 金额:$ 4.96万
- 依托单位:
- 依托单位国家:美国
- 项目类别:Standard Grant
- 财政年份:1996
- 资助国家:美国
- 起止时间:1996-09-01 至 1998-05-31
- 项目状态:已结题
- 来源:
- 关键词:
项目摘要
9616391 Olurotimi Recurrent neural networks (RNN) are nonlinear dynamical filters, and it has been shown by J. Lo that they are capable of converging to the minimum variance filter for a signal process. However, unlike conventional filtering techniques that utilize top-down, parameteric design to realize the filters, the RNN approach is a data-driven synthesis approach. the neural network approach is justified by several universal approximation theorems that ensure that the neural network form is theoretically sufficient for implementing these tasks. However, one feature of neural network design familiar to designers and users alike is that may different (e.g. in weights) networks can be constructed to solve the same problem. This project will employ novel concepts and quantitative results on the behavior of RNN's in noise in order to address this problem. Recognizing the important existence results of Lo, and using recent results of Olurotimi and Das, the PI develops a modified training measure. The resulting ordered derivatives training scheme of Werbos the searches not for must any optimum weight set, but for the restricted class of optimum weight sets that also increase the estimator efficiency. The proposed research will result in s design scheme expected to significantly reduce the design time of nonlinear RNN filters.
9616391 Olurotimi循环神经网络(RNN)是非线性动态滤波器,J. Lo已证明它们能够收敛到信号处理的最小方差滤波器。 然而,与利用自顶向下的参数化设计来实现滤波器的传统滤波技术不同,RNN方法是一种数据驱动的综合方法。 神经网络方法由几个通用近似定理证明,这些通用近似定理确保神经网络形式在理论上足以实现这些任务。 然而,设计者和用户都熟悉的神经网络设计的一个特征是,可以构建不同的(例如权重)网络来解决相同的问题。 该项目将采用新的概念和定量结果对噪声中的RNN的行为,以解决这个问题。 PI认识到Lo的重要存在结果,并使用Olurotimi和Das的最新结果,开发了一种改良的培训措施。 由此产生的Werbos的有序导数训练方案的搜索不一定是任何最优权重集,但对于有限类的最优权重集,也增加了估计器的效率。 所提出的研究将导致的设计方案,预计将显着减少非线性RNN滤波器的设计时间。
项目成果
期刊论文数量(0)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
数据更新时间:{{ journalArticles.updateTime }}
{{
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 }}
Oluseyi Olurotimi其他文献
Oluseyi Olurotimi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('Oluseyi Olurotimi', 18)}}的其他基金
Neural Network Derivatives Pricing for Electricity Commodity Markets
电力商品市场的神经网络衍生品定价
- 批准号:
9908086 - 财政年份:1999
- 资助金额:
$ 4.96万 - 项目类别:
Standard Grant
Neural Network Dynamic Pattern Recognition Using Optimal Control
使用最优控制的神经网络动态模式识别
- 批准号:
9209456 - 财政年份:1992
- 资助金额:
$ 4.96万 - 项目类别:
Standard Grant
相似海外基金
New approaches to training deep probabilistic models
训练深度概率模型的新方法
- 批准号:
2613115 - 财政年份:2025
- 资助金额:
$ 4.96万 - 项目类别:
Studentship
ARC Training Centre for Automated Vehicles in Rural and Remote Regions
ARC农村和偏远地区自动驾驶汽车培训中心
- 批准号:
IC230100001 - 财政年份:2024
- 资助金额:
$ 4.96万 - 项目类别:
Industrial Transformation Training Centres
DMS-EPSRC: Asymptotic Analysis of Online Training Algorithms in Machine Learning: Recurrent, Graphical, and Deep Neural Networks
DMS-EPSRC:机器学习中在线训练算法的渐近分析:循环、图形和深度神经网络
- 批准号:
EP/Y029089/1 - 财政年份:2024
- 资助金额:
$ 4.96万 - 项目类别:
Research Grant
C-NEWTRAL: smart CompreheNsive training to mainstrEam neW approaches for climaTe-neutRal cities through citizen engAgement and decision-making support
C-NEWTRAL:智能综合培训,通过公民参与和决策支持将气候中和城市的新方法纳入主流
- 批准号:
EP/Y032640/1 - 财政年份:2024
- 资助金额:
$ 4.96万 - 项目类别:
Research Grant
Intelligent Breast Cancer DiagnOsis and MonItoring Therapeutic Response Training Network (CanDoIt)
智能乳腺癌诊断和监测治疗反应训练网络(CanDoIt)
- 批准号:
EP/Y03693X/1 - 财政年份:2024
- 资助金额:
$ 4.96万 - 项目类别:
Research Grant
TARGET Mineral Resources - Training And Research Group for Energy Transition Mineral Resources
TARGET 矿产资源 - 能源转型矿产资源培训与研究小组
- 批准号:
NE/Y005457/1 - 财政年份:2024
- 资助金额:
$ 4.96万 - 项目类别:
Training Grant
Collaborative Research: CyberTraining: Pilot: PowerCyber: Computational Training for Power Engineering Researchers
协作研究:CyberTraining:试点:PowerCyber:电力工程研究人员的计算培训
- 批准号:
2319895 - 财政年份:2024
- 资助金额:
$ 4.96万 - 项目类别:
Standard Grant
Collaborative Research: CyberTraining: Implementation: Medium: Training Users, Developers, and Instructors at the Chemistry/Physics/Materials Science Interface
协作研究:网络培训:实施:媒介:在化学/物理/材料科学界面培训用户、开发人员和讲师
- 批准号:
2321102 - 财政年份:2024
- 资助金额:
$ 4.96万 - 项目类别:
Standard Grant
Project Incubation: Training Undergraduates in Collaborative Research Ethics
项目孵化:培养本科生合作研究伦理
- 批准号:
2316154 - 财政年份:2024
- 资助金额:
$ 4.96万 - 项目类别:
Standard Grant
REU Site: ASL-English Bilingual Cognitive and Educational Neuroscience Training and Research Experience (ASL-English Bilingual CENTRE)
REU网站:ASL-英语双语认知和教育神经科学培训和研究经验(ASL-英语双语中心)
- 批准号:
2349454 - 财政年份:2024
- 资助金额:
$ 4.96万 - 项目类别:
Standard Grant