期刊文献+
共找到11篇文章
< 1 >
每页显示 20 50 100
模式神经元网络的聚类方法研究 被引量:2
1
作者 代小娟 林小竹 周晓正 《北京石油化工学院学报》 2009年第4期13-16,共4页
为了更好地模拟人脑对事物的学习、认知过程,笔者提出了模式神经元网络的聚类规则和方法,从而完善了这种新型的神经网络模型。与现有的人工神经网络不同,模式神经元网络不需要反复迭代就能达到学习、识别、分类的效果。实验结果表明:与... 为了更好地模拟人脑对事物的学习、认知过程,笔者提出了模式神经元网络的聚类规则和方法,从而完善了这种新型的神经网络模型。与现有的人工神经网络不同,模式神经元网络不需要反复迭代就能达到学习、识别、分类的效果。实验结果表明:与自适应共振理论相比,模式神经元网络的学习效率快,识别精度高,分类效果也比较好。 展开更多
关键词 人工神经网络 模式神经元 聚类 阈值
下载PDF
神经元模式分类器学习的进化计算算法
2
作者 刘健勤 魏敏洁 《计算机应用与软件》 CSCD 2000年第10期34-38,共5页
本文提出了一种用于神经元模式分类器学习的进化计算算法。该算法综合了非确定有限自动机和次群体的动态数据结构,可有效地完成神经网络模式分类器的结构学习,以获得最优的求解结果。该算法的有效性已由计算机仿真实验所证实,可被认为... 本文提出了一种用于神经元模式分类器学习的进化计算算法。该算法综合了非确定有限自动机和次群体的动态数据结构,可有效地完成神经网络模式分类器的结构学习,以获得最优的求解结果。该算法的有效性已由计算机仿真实验所证实,可被认为是一种很有发展前途的模式分类系统的机器学习算法。 展开更多
关键词 进化计算 神经网络 算法 神经元模式分类器
下载PDF
基于神经元激活模式控制的深度学习训练数据泄露诱导 被引量:3
3
作者 潘旭东 张谧 杨珉 《计算机研究与发展》 EI CSCD 北大核心 2022年第10期2323-2337,共15页
开放网络下分布式深度学习的兴起带来潜在的数据泄露风险.作为分布式模型构建中的重要信息载体,训练梯度是模型和端侧数据共同计算的产物,包含参与计算的私密用户数据信息.因此,近年的研究工作针对训练梯度提出一系列新型攻击方法.其中... 开放网络下分布式深度学习的兴起带来潜在的数据泄露风险.作为分布式模型构建中的重要信息载体,训练梯度是模型和端侧数据共同计算的产物,包含参与计算的私密用户数据信息.因此,近年的研究工作针对训练梯度提出一系列新型攻击方法.其中,尤以数据重建攻击(data reconstruction attack)所造成的攻击效果最佳:仅从深度神经网络的平均训练梯度中,攻击者即可近乎无损地恢复一个训练数据批次的各个样本.然而,已有数据重建攻击大多仅停留在攻击方法设计和实验验证层面,对重要实验现象缺乏深层机理分析.尽管有研究发现,满足特定神经元激活独占性(exclusivity)条件的任意大小训练数据批次能被攻击者从训练梯度中像素级重建,然而,实证研究表明在实际训练数据中满足该条件的训练数据批次比例较少,难以造成实际泄露威胁.为增强上述攻击的有效性和应用范围,提出基于线性规划的神经元激活模式控制算法,为给定训练批次生成微小扰动,从而满足神经元激活独占性,以增强后续数据重建攻击效能.在实际中,通过在端侧节点部署该算法,半诚实(honest-but-curious)分布式训练服务能诱导本地训练批次的训练梯度具有理论保证的可重建性.在5个涵盖人脸识别、智能诊断的数据集上的实验结果表明,提出方法在与原始攻击算法重建效果持平的情况下,将可重建训练批次大小从8张提升至实际应用大小,并提升攻击效率10倍以上. 展开更多
关键词 深度学习隐私 神经元激活模式 深度学习 人工智能 信息安全
下载PDF
浅谈脑卒中治疗的神经元治疗模式
4
作者 谭凤喜 《中国民族民间医药》 2013年第17期89-90,共2页
医疗模式是指导医疗实践的指导思想,脑卒中治疗以血管为治疗核心属于血管治疗模式,以神经元为治疗核心则属于神经元治疗模式。运用中药破血化瘀、泄热醒神、祛腐生新之剂,促进神经元再生;选用头针调节神经传导,运动疗法改善肢体运动功能... 医疗模式是指导医疗实践的指导思想,脑卒中治疗以血管为治疗核心属于血管治疗模式,以神经元为治疗核心则属于神经元治疗模式。运用中药破血化瘀、泄热醒神、祛腐生新之剂,促进神经元再生;选用头针调节神经传导,运动疗法改善肢体运动功能,促进神经功能恢复。从神经元再生角度而不是从血管治疗角度去评价各种治疗方法,这是神经元治疗模式的特有要求。 展开更多
关键词 脑卒中 神经元治疗模式 神经再生
下载PDF
一种改进的人工神经网络模型 被引量:3
5
作者 周晓正 林小竹 +1 位作者 陈星 李玉龙 《计算机工程与应用》 CSCD 北大核心 2008年第9期64-66,69,共4页
提出一种新型人工神经网络模型,称为"基于模式神经元的人工神经网络(Pattern Neuron Based Artificial Neural Net-work,PNBANN)"。与现有的神经计算网络不同,PNBANN是一种完全基于神经元连接的网络模型。网络中的每一个神经... 提出一种新型人工神经网络模型,称为"基于模式神经元的人工神经网络(Pattern Neuron Based Artificial Neural Net-work,PNBANN)"。与现有的神经计算网络不同,PNBANN是一种完全基于神经元连接的网络模型。网络中的每一个神经元都唯一代表一种模式,每当接收新模式时,自动建立一个新的连接,把信息存储在网络中;而接收已有的模式时,已有的神经元连接得到加强。当模式神经元的输出达到所设定的感觉阈值时,对应模式的信息被记忆。因此,PNBANN就是不断地接收、存储各种信息,并把感觉足够强的模式记忆下来,这一过程更接近于人脑的学习、记忆过程。实验结果证明,PNBANN学习效率高,在学习新知识时不会影响已有的知识,同时具有很强的识别能力。 展开更多
关键词 模式神经元 人工神经网络 感觉闽值
下载PDF
In- and Anti-transition of Firing Patterns Induced by Random Long-range Connections in Coupled Hindmarsh-Rose Neurons System 被引量:1
6
作者 王鹏 张季谦 任海林 《Chinese Journal of Chemical Physics》 SCIE CAS CSCD 2010年第1期23-29,I0001,共8页
The effects of random long-range connections (shortcuts) on the transitions of neural firing patterns in coupled Hindmarsh-Rose neurons are investigated, where each neuron is subjected to an external current. It is ... The effects of random long-range connections (shortcuts) on the transitions of neural firing patterns in coupled Hindmarsh-Rose neurons are investigated, where each neuron is subjected to an external current. It is found that, on one hand, the system can achieve the transition of neural firing patterns from the fewer-period state to the multi-period one, when the number of the added shortcuts in the neural network is greater than a threshold value, indicating the occurrence of in-transition of neural firing patterns. On the other hand, for a stronger coupling strength, we can also find the similar but reverse results by adding some proper random connections. In addition, the influences of system size and coupling strength on such transition behavior, as well as the internality between the transition degree of firing patterns and its critical characteristics for different external stimulation current, are also discussed. 展开更多
关键词 In- and anti-transition Random long-range connection Firing pattern System size
下载PDF
A Neural Network Constructing Method Based on Many Kinds of Neurons Model 被引量:2
7
作者 WANG Xianbao CAO Wenming +1 位作者 FENG Hao WANG Shoujue 《通讯和计算机(中英文版)》 2005年第1期31-33,共3页
关键词 人工神经网络 神经元模式 人工智能化 计算机技术
下载PDF
A review for dynamics of collective behaviors of network of neurons 被引量:21
8
作者 MA Jun TANG Jun 《Science China(Technological Sciences)》 SCIE EI CAS CSCD 2015年第12期2038-2045,共8页
The nervous system is composed of a large number of neurons, and the electrical activities of neurons can present multiple modes during the signal transmission between neurons by changing intrinsic bifurcation paramet... The nervous system is composed of a large number of neurons, and the electrical activities of neurons can present multiple modes during the signal transmission between neurons by changing intrinsic bifurcation parameters or under appropriate external forcing. In this review, the dynamics for neuron, neuronal network is introduced, for example, the mode transition in electrical activity, functional role of autapse connection, bifurcation verification in biological experiments, interaction between neuron and astrocyte, noise effect, coherence resonance, pattern formation and selection in network of neurons. Finally, some open problems in this field such as electromagnetic radiation on electrical activities of neuron, energy consumption in neurons are presented. 展开更多
关键词 Neuronal network DEFECTS spiral wave target wave electromagnetic induction
原文传递
Synchronization of two electrically coupled inspiratory pacemaker neurons 被引量:7
9
作者 YE WeiJie LIU ShenQuan LIU XuanLiang 《Science China(Technological Sciences)》 SCIE EI CAS 2014年第5期929-935,共7页
Synchronization is considered to be a crucial mechanism that maintains respiratory rhythm.For understanding the effect of electrical coupling on the transition of the firing patterns and synchronization,we coupled two... Synchronization is considered to be a crucial mechanism that maintains respiratory rhythm.For understanding the effect of electrical coupling on the transition of the firing patterns and synchronization,we coupled two inspiratory pacemaker neurons together,and studied various synchronous behaviors between them.We firstly compared the bifurcation diagrams between the coupled neurons and single neuron,and found that the coupled neurons had a more complicated bifurcation mode.By increasing the coupling strength,the regular variation of phase differences was illustrated so that asynchronous and some synchronous states could be observed.These synchronous states were also shown in detail by phase portraits and firing series.In addition,we explored the ranges of different synchronous states,which attributed to different ranges of membrane capacitance and coupling strength. 展开更多
关键词 SYNCHRONIZATION inspiratory pacemaker neuron phase differences electrical coupling BIFURCATION
原文传递
Distribution Assessment and Source Identification Using Multivariate Statistical Analyses and Artificial Neutral Networks for Trace Elements in Agricultural Soils in Xinzhou of Shanxi Province, China 被引量:2
10
作者 SHANGGUAN Yuxian CHENG Bin +9 位作者 ZHAO Long HOU Hong MA Jin SUN Zaijin XU Yafei ZHAO Ruifen ZHANG Yigong HUA Xiaozan HUO Xiaolan ZHAO Xiufeng 《Pedosphere》 SCIE CAS CSCD 2018年第3期542-554,共13页
Multivariate statistical analyses were used to assess the contents and distributions of trace elements in agricultural soils in Xinzhou of Shanxi Province, China, and to identify their sources. Samples with high level... Multivariate statistical analyses were used to assess the contents and distributions of trace elements in agricultural soils in Xinzhou of Shanxi Province, China, and to identify their sources. Samples with high levels of trace elements were concentrated in eastern Xinzhou, with contents declining from the east to west. Principal component and redundancy analyses revealed strong correlations among Co, Cu, Mn, Ni, Se, V, and Zn contents, suggesting that these elements were derived from similar parent materials. There were also strong correlations between the contents of these elements and soil properties. Contents of Cd and Pb were significantly higher in the agricultural soil samples than in the background soil samples(P < 0.05), and were higher in areas with higher levels of gross domestic product but decreased with distance to the nearest road. Therefore, human activities appear to have a strong influence on the Cd and Pb distribution patterns. A novel artificial neural network(ANN) model, using environmental input data, was used to predict the soil Cd and Pb contents of specified test dates. The performances of the ANN model and a traditional multilinear model were compared. The ANN model could successfully predict Cd and Pb content distributions, projecting that soil Cd and Pb contents will increase by 128% and 25%, respectively, by 2020. The results thus indicated that the economic condition of an area has a greater effect on trace element contents and distributions in the soil than the scale of the economy itself. 展开更多
关键词 CONTAMINATION enrickment factor keavy metal prediction principal component analysis redundancy analysis
原文传递
On brain activity mapping: Insights and lessons from Brain Decoding Project to map memory patterns in the hippocampus 被引量:1
11
作者 TSIEN Joe Z. LI Meng +9 位作者 OSAN Remus CHEN GuiFen LIN LongNian WANG Phillip Lei FREY Sabine FREY Julietta ZHU DaJiang LIU TianMing ZHAO Fang KUANG Hui 《Science China(Life Sciences)》 SCIE CAS 2013年第9期767-779,共13页
The BRAIN project recently announced by the president Obama is the reflection of unrelenting human quest for cracking the brain code, the patterns of neuronal activity that define who we are and what we are. While the... The BRAIN project recently announced by the president Obama is the reflection of unrelenting human quest for cracking the brain code, the patterns of neuronal activity that define who we are and what we are. While the Brain Activity Mapping proposal has rightly emphasized on the need to develop new technologies for measuring every spike from every neuron, it might be helpful to consider both the theoretical and experimental aspects that would accelerate our search for the organizing principles of the brain code. Here we share several insights and lessons from the similar proposal, namely, Brain Decoding Project that we initiated since 2007. We provide a specific example in our initial mapping of real-time memory traces from one part of the memory circuit, namely, the CA1 region of the mouse hippocampus. We show how innovative behavioral tasks and appropriate mathematical analyses of large datasets can play equally, if not more, important roles in uncovering the specific-to-general feature-coding cell assembly mechanism by which episodic memory, semantic knowledge, and imagination are generated and organized. Our own experiences suggest that the bottleneck of the Brain Project is not only at merely developing additional new technologies, but also the lack of efficient avenues to disseminate cutting edge platforms and decoding expertise to neuroscience community. Therefore, we propose that in order to harness unique insights and extensive knowledge from various investigators working in diverse neuroscience subfields, ranging from perception and emotion to memory and social behaviors, the BRAIN project should create a set of International and National Brain Decoding Centers at which cutting-edge recording technologies and expertise on analyzing large datasets analyses can be made readily available to the entire community of neuroscientists who can apply and schedule to perform cutting-edge research. 展开更多
关键词 BRAIN project Brain Decoding Project brain activity map learning and memory episodic memory semantic knowledge IMAGINATION concepts fear conditioning earthquake experiences neural code
原文传递
上一页 1 下一页 到第
使用帮助 返回顶部