检索结果-南通市图书馆

Enhanced memory capacity of a neuromorphic reservoir computing system based on a VCSEL with double optical feedbacks

引用

Science China(Information Sciences) 2020年第6期63卷 164-175页

作者： Xingxing GUO Shuiying XIANG Yahui ZHANG Aijun WEN Yue HAO State Key Laboratory of Integrated Service Networks Xidian University State Key Discipline Laboratory of Wide Bandgap Semiconductor Technology School of Microelectronics Xidian University

In this paper, a neuromorphic reservoir computing(RC) system with enhanced memory capacity(MC) based on a vertical-cavity surface-emitting laser(VCSEL) subject to double optical feedbacks(DOF)is proposed and investigated numerically. The aim of this study is to explore the MC of the proposed *** the purpose of comparison, the MC of the VCSEL-based RC system with single optical feedback(SOF)is also taken into account. It is found that, compared with the VCSEL-based RC system subject to SOF,enhanced MC can be obtained for the VCSEL-based RC system with DOF. Besides, the effects of feedback strength, injected strength, frequency detuning as well as injection current on the MC of the VCSEL-based RC system with DOF are considered. Moreover, the influence of feedback delays is also carefully ***, such proposed VCSEL-based RC system with DOF provides a prospect for the further development of the neuromorphic photonic system based on RC.

关键词： vertical-cavity surface-emitting laser nanophotonic reservoir computing memory capacity double feedback information processing

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

SMConf: One-Size-Fit-Bunch, Automated memory capacity Configuration for In-memory Data Analytic Platform

引用

Computers, Materials & Continua 2021年第2期66卷 1697-1717页

作者： Yi Liang Shaokang Zeng Xiaoxian Xu Shilu Chang Xing Su Faculty of Information Technology Beijing University of TechnologyBeijing100124China Department of Informatics University of ZurichZurichCH-8050Switzerland

Spark is the most popular in-memory processing framework for big data *** is the crucial resource for workloads to achieve performance acceleration on *** extant memory capacity configuration approach in Spark is to statically configure the memory capacity for workloads based on user’s ***,without the deep knowledge of the workload’s system-level characteristics,users in practice often conservatively overestimate the memory utilizations of their workloads and require resource manager to grant more memory share than that they actually need,which leads to the severe waste of memory *** address the above issue,SMConf,an automated memory capacity configuration solution for in-memory computing workloads in Spark is *** is designed based on the observation that,though there is not one-size-fit-all proper configuration,the one-size-fit-bunch configuration can be found for in-memory computing *** classifies typical Spark workloads into categories based on metrics across layers of Spark system *** each workload category,an individual memory requirement model is learned from the workload’s input data size and the strong-correlated configuration *** an ad-hoc workload,SMConf matches its memory requirement signature to one of the workload categories with small-sized input data and determines its proper memory capacity configuration with the corresponding memory requirement *** results demonstrate that,compared to the conservative default configuration,SMConf can reduce the memory resource provision to Spark workloads by up to 69%with the slight performance degradation,and reduce the average turnaround time of Spark workloads by up to 55%in the multi-tenant environments.

关键词： Spark memory capacity automated configuration

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

On the Current Error Based Sampled-data Iterative Learning Control with Reduced memory capacity

引用

International Journal of Automation and computing 2015年第3期12卷 307-315页

作者： Chiang-Ju Chien Yu-Chung Hung Rong-Hu Chi Department of Electronic Engineering Huafan University School of Automation and Electrical Engineering Qingdao University of Science and Technology

The design of iterative learning controller(ILC) requires to store the system input, output or control parameters of previous trials for generating the input of the current trial. In order to apply the iterative learning controller for a real application and reduce the memory size for implementation, a current error based sampled-data proportional-derivative(PD) type iterative learning controller is proposed for control systems with initial resetting error, input disturbance and output measurement noise in this *** proposed iterative learning controller is simple and effective. The first contribution in this paper is to prove the learning error convergence via a rigorous technical analysis. It is shown that the learning error will converge to a residual set if a forgetting factor is introduced in the controller. All the theoretical results are also shown by computer simulations. The second main contribution is to realize the iterative learning controller by a digital circuit using a field programmable gate array(FPGA) chip applied to repetitive position tracking control of direct current(DC) motors. The feasibility and effectiveness of the proposed current error based sampleddata iterative learning controller are demonstrated by the experiment results. Finally, the relationship between learning performance and design parameters are also discussed extensively.

关键词： Iterative learning control current error sampled-data system memory capacity field programmable gate array(FPGA) chip.

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

On memory capacity of the Probabilistic Logic Neuron Network

引用

Journal of Computer Science & Technology 1993年第3期8卷 252-256页

作者：张钹张铃 Dept.of Computer Science and Technology Tsinghua UniversityBeijing 100084 Dept.of Mathematics Anqing Teachers' CollegeAnqingAnhui 246011

In this paper,the memory capacity of Probabilistic Logic Neuron(PLN)network is discussed. We obtain two main results:(1)the method for constructing a PLN network with a given memory capacity;(2)the relationship between the memory capacity and the size of a PLN *** show that the memory capacity of a PLN network depends on not only the number of input ports of its element but also the number of elements *** results provide a new method for designing a PLN network.

关键词： PLN network memory capacity

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

A Chessboard Model of Human Brain and An Application on memory capacity

引用

Journal of Applied Mathematics and Physics 2016年第2期4卷 359-367页

作者： Chenxia Gu Shaotong Wang Hao Yu Department of Mathematical Sciences Xi’an Jiaotong-Liverpool University Suzhou China

The famous claim that we only use about 10% of the brain capacity has recently been challenged. Researchers argue that we are likely to use the whole brain, against the 10% claim. Some evidence and results from relevant studies and experiments related to memory in the field of neuroscience lead to the conclusion that if the rest 90% of the brain is not used, then many neural pathways will degenerate. What is memory? How does the brain function? What would be the limit of memory capacity? This article provides a model established upon the physiological and neurological characteristics of the human brain, which can give some theoretical support and scientific explanation to explain some phenomena. It may not only have theoretically significance in neuroscience, but can also be practically useful to fill in the gap between the natural and machine intelligence.

关键词： memory capacity Excitation Transmission Neuroscience Machine Intelligence

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

The Generalized Hopfield Network And Associative memory

The Generalized Hopfield Network And Associative Memory

引用

1999年中国神经网络与信号处理学术会议

作者： Ma Jinwen Institute of Mathematics,Shantou University Shantou,Guangdoug,515063

This paper summarizes a series of our researches on the generalized Hopfield network for associative ***,the stability of the generalized Hopfield network is *** the memory capacity of the generalized Hopfield network is discussed and a lower and an upper bounds of it are ***,a learning algorithm referred to as the object perceptron learning algorithm is proposed on the generalized Hopfield network for associative memory.

关键词： Neural network Generalized Hopfield network Associative memory Stability memory capacity Learning algorithm

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

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：