共查询到20条相似文献，搜索用时 21 毫秒
1.
2.
3.
人工神经网络在地球物理领域中，尤其在模式识别和油气预测方面得到了较好的应用．前向网络的重要特性是能够总结、归纳已知样本隐含的函数关系．然而其推广性能有待进一步研究．本文强调了该问题的重要性并提出了改善网络推广性能的技术，即在网络学习过程中，不仅让总误差下降，还尽可能使建立的“隐函数”平滑．计算实例表明，本文的算法可以明显地改善网络的推广性能．最后给出了用该技术在辽河油田进行油气预测的实例 相似文献
4.
5.
针对标准的BP神经网络对于声音信号识别率不高的问题,提出了一种用粒子群算法（PSO）优化BP神经网络的算法,建立了声音信号识别模型。PSO优化BP神经网络主要是用PSO来优化BP神经网络的初始权值和闽值,然后通过训练BP神经网络得到识别模型的最优解,优化后的神经网络具有误判率小、反应速度快等特点。在实验中把标准的BP神经网络和PSO优化后的BP神经网络用于八种异常声音的MFCC特征量和差分MFCC特征量识别,结果表明：在声音信号的识别系统中采用PSO优化BP神经网络的算法提高了系统的识别性能,达到了系统设计的目的。 相似文献
6.
动物都需要认识和学习外界环境因素,并根据价值与风险做出抉择与行动;社会动物还必须有社会认知、共情、社会交往等社会行为能力;而人类有发达的自我认知、逻辑推演、意识、语言等能力。动物认知能力的好坏,决定了动物在野外是否能够成功觅食、躲避天敌、繁衍后代;而人类认知能力,则决定了个人的人生轨迹、自我价值实现乃至对社会的贡献。所有这些认知行为都是由神经细胞的功能来决定,其神经基础是脑科学的核心问题,也是人类认识自身的终极挑战。经过多年的研究,神经科学已经揭示了认知行为神经基础的一些基本原理:不同认知行为是由脑内不同的神经环路负责,需要各脑区内的局部神经环路与脑区间长程神经环路的协同工作;学习与记忆是许多认知功能的必要基础,这是由神经细胞之间突触联结的强度与结构的可塑性介导;神经调质(例如多巴胺)可以在多个尺度上调节神经网络的活动与可塑性,从而调控认知行为。文章聚焦在感知觉、学习与记忆、抉择、社会行为、意识和运动控制等方面,对认知功能的神经基础进行了概述。我们认为,未来神经科学需要结合介观和微观尺度的研究,对认知行为的神经基础进行系统与深入的阐明。在介观层面,科学家们需要描绘脑区之间细胞类型特异性的联结图谱;绘制认知功能的大脑功能图谱;利用因果性手段、揭示认知功能的核心脑区;操控不同脑区及脑区间联结的活动,进而观察认知行为的改变和其他参与环路的活动变化,从而获得脑整体动态规律。在微观层面,需要阐明不同脑区有哪些特定类型的神经元;揭示不同类型神经元是如何参与特定认知功能的;解析不同类型的神经元是如何联结以及这些联结是如何在认知行为中发生动态改变的。这些介观与微观研究将为理解宏观认知行为的神经基础提供重要线索,对于破解人类智能这一终极奥秘具有重要意义。同时,揭示认知行为的神经机制还是治疗脑疾病的必要基础,而且有助于推动脑启发(Brain Inspired)的智能技术的发展。 相似文献
7.
基于BP神经网络的印刷体数字识别研究 总被引：1，自引：0，他引：1
BP神经网络是一种误差逆传播算法训练的多层前馈网络,具备网络学习能力强、输入/输出模式映射关系存贮量大、事先不需要描述输入/输出映射关系等诸多优点的数学方程。本文通过BP神经网络的介绍,利用不变矩特征提取方法设计一种有效的BP神经网络印刷体数字识别演示系统,对印刷体数字识别的深入研究具有一定的指导意义。 相似文献
8.
Lazear (2005) suggests that entrepreneurs should be generalists, while those who work for others should be specialists. Many prospective entrepreneurs will develop varied skills by engaging in a variety of employment activities prior to becoming an entrepreneur, and incomes are higher for those that do so. An alternative view predicts that those with greater taste for variety are more likely to become entrepreneurs. Varied employment prior to becoming an entrepreneur is simply an expression of this taste, and is associated with lower earnings. Data from a survey of 830 independent inventors and 300 individuals from the general population are used to discriminate between these two theories. The results show that inventor-entrepreneurs typically have a more varied labor market experience, and that varied work experience is associated with lower household income. 相似文献
9.
This paper addresses the problem of the automatic recognition and classification of temporal expressions and events in human language. Efficacy in these tasks is crucial if the broader task of temporal information processing is to be successfully performed. We analyze whether the application of semantic knowledge to these tasks improves the performance of current approaches. We therefore present and evaluate a data-driven approach as part of a system: TIPSem. Our approach uses lexical semantics and semantic roles as additional information to extend classical approaches which are principally based on morphosyntax. The results obtained for English show that semantic knowledge aids in temporal expression and event recognition, achieving an error reduction of 59% and 21%, while in classification the contribution is limited. From the analysis of the results it may be concluded that the application of semantic knowledge leads to more general models and aids in the recognition of temporal entities that are ambiguous at shallower language analysis levels. We also discovered that lexical semantics and semantic roles have complementary advantages, and that it is useful to combine them. Finally, we carried out the same analysis for Spanish. The results obtained show comparable advantages. This supports the hypothesis that applying the proposed semantic knowledge may be useful for different languages. 相似文献
10.
神经元作为神经系统的基本单元,提供了人类认知的基本信息功能处理机制。文章通过对神经元及其模型进行计算分析,指出了神经元内离子对刺激信息的反应,在此基础上阐释了误差驱动任务学习与BP学习法,最后文章对神经元的计算启示给出了解读。文章表明,脑认知是动态的表征,其非线性地处理认知现象,并指出计算神经科学在解读大脑处理信息上正在尝试突破,具有重要的研究意义和价值。 相似文献
11.
Iti Chaturvedi Edoardo Ragusa Paolo Gastaldo Rodolfo Zunino Erik Cambria 《Journal of The Franklin Institute》2018,355(4):1780-1797
Subjectivity detection is a task of natural language processing that aims to remove ‘factual’ or ‘neutral’ content, i.e., objective text that does not contain any opinion, from online product reviews. Such a pre-processing step is crucial to increase the accuracy of sentiment analysis systems, as these are usually optimized for the binary classification task of distinguishing between positive and negative content. In this paper, we extend the extreme learning machine (ELM) paradigm to a novel framework that exploits the features of both Bayesian networks and fuzzy recurrent neural networks to perform subjectivity detection. In particular, Bayesian networks are used to build a network of connections among the hidden neurons of the conventional ELM configuration in order to capture dependencies in high-dimensional data. Next, a fuzzy recurrent neural network inherits the overall structure generated by the Bayesian networks to model temporal features in the predictor. Experimental results confirmed the ability of the proposed framework to deal with standard subjectivity detection problems and also proved its capacity to address portability across languages in translation tasks. 相似文献
12.
[研究目的]科学数据已经成为科研产出的重要成果类型之一,通过研究和观察科学数据的使用情况可以发现科学数据的管理需求,提高科研人员共享和重用科学数据的积极性。[研究方法]以生物信息学领域学术论文全文信息作为研究对象,利用规则抽取和人工标注形成了生物信息学引文分类数据集,并对比评估了8种机器学习方法在数据集上的分类和识别效果。[研究结论]实证研究效果显示,机器学习分类方法可以用于科学数据正式引用识别,全文信息和样本集大小对分类效果起到关键性作用。 相似文献
13.
《Journal of The Franklin Institute》2023,360(8):5481-5503
Neural decoders were introduced as a generalization of the classic Belief Propagation (BP) decoding algorithms. In this work, we propose several neural decoders with different permutation invariant structures for BCH codes and punctured RM codes. Firstly, we propose the cyclically equivariant neural decoder which makes use of the cyclically invariant structure of these two codes. Next, we propose an affine equivariant neural decoder utilizing the affine invariant structure of those two codes. Both these two decoders outperform previous neural decoders when decoding cyclic codes. The affine decoder achieves a smaller decoding error probability than the cyclic decoder, but it usually requires a longer running time. Similar to using the property of the affine invariant property of extended BCH codes and RM codes, we propose the list decoding version of the cyclic decoder that can significantly reduce the frame error rate(FER) for these two codes. For certain high-rate codes, the gap between the list decoder and the Maximum Likelihood decoder is less than 0.1 dB when measured by FER. 相似文献
14.
《Information processing & management》2022,59(4):102953
Aspect-based sentiment analysis technologies may be a very practical methodology for securities trading, commodity sales, movie rating websites, etc. Most recent studies adopt the recurrent neural network or attention-based neural network methods to infer aspect sentiment using opinion context terms and sentence dependency trees. However, due to a sentence often having multiple aspects sentiment representation, these models are hard to achieve satisfactory classification results. In this paper, we discuss these problems by encoding sentence syntax tree, words relations and opinion dictionary information in a unified framework. We called this method heterogeneous graph neural networks (Hete_GNNs). Firstly, we adopt the interactive aspect words and contexts to encode the sentence sequence information for parameter sharing. Then, we utilized a novel heterogeneous graph neural network for encoding these sentences’ syntax dependency tree, prior sentiment dictionary, and some part-of-speech tagging information for sentiment prediction. We perform the Hete_GNNs sentiment judgment and report the experiments on five domain datasets, and the results confirm that the heterogeneous context information can be better captured with heterogeneous graph neural networks. The improvement of the proposed method is demonstrated by aspect sentiment classification task comparison. 相似文献
15.
16.
《Information processing & management》2022,59(4):102957
The identification of knowledge graph entity mentions in textual content has already attracted much attention. The major assumption of existing work is that entities are explicitly mentioned in text and would only need to be disambiguated and linked. However, this assumption does not necessarily hold for social content where a significant portion of information is implied. The focus of our work in this paper is to identify whether textual social content include implicit mentions of knowledge graph entities or not, hence forming a two-class classification problem. To this end, we adopt the systemic functional linguistic framework that allows for capturing meaning expressed through language. Based on this theoretical framework we systematically introduce two classes of features, namely syntagmatic and paradigmatic features, for implicit entity recognition. In our experiments, we show the utility of these features for the task, report on ablation studies, measure the impact of each feature subset on each other and also provide a detailed error analysis of our technique. 相似文献
17.
指纹识别技术是当今应用最广泛的生物识别技术之一。在指纹识别过程中,图像处理、特征提取、匹配等过程数据量庞大,计算比较烦琐。BP神经网络具有良好的自学习能力、强大的分类能力和容错能力,将其应用到指纹识别中是可行的。为改进BP神经网络计算速度较慢,梯度下降法不能处理一些不可微传递函数的问题,采用粒子群算法对BP算法进行优化,提高了指纹识别的速度和准确度。 相似文献
18.
基于CBERS-1图像的干旱半干旱区土地利用分类 总被引：5，自引：0，他引：5
以中巴资源卫星CBERS 1图像数据为信息源,分别采用最大似然法、BP神经网络和Fuzzy ARTMAP神经网络 3种分类器,以位于干旱区的中国新疆石河子地区为例,进行了土地利用计算机自动分类。结果认为,3种方法中以Fuzzy ARTMAP神经网络法分类精度最高,分别比最大似然法和BP神经网络法提高了 1 0.69%和 6.84%。同时也证实了CBERS 1图像在土地利用调查中的实用性 相似文献
19.
Alaa Mohasseb Mohamed Bader-El-Den Mihaela Cocea 《Information processing & management》2018,54(6):1228-1243
Question-answering has become one of the most popular information retrieval applications. Despite that most question-answering systems try to improve the user experience and the technology used in finding relevant results, many difficulties are still faced because of the continuous increase in the amount of web content. Questions Classification (QC) plays an important role in question-answering systems, with one of the major tasks in the enhancement of the classification process being the identification of questions types. A broad range of QC approaches has been proposed with the aim of helping to find a solution for the classification problems; most of these are approaches based on bag-of-words or dictionaries. In this research, we present an analysis of the different type of questions based on their grammatical structure. We identify different patterns and use machine learning algorithms to classify them. A framework is proposed for question classification using a grammar-based approach (GQCC) which exploits the structure of the questions. Our findings indicate that using syntactic categories related to different domain-specific types of Common Nouns, Numeral Numbers and Proper Nouns enable the machine learning algorithms to better differentiate between different question types. The paper presents a wide range of experiments the results show that the GQCC using J48 classifier has outperformed other classification methods with 90.1% accuracy. 相似文献
20.
Current deep-learning models are mostly built upon neural networks, i.e. multiple layers of parameterized differentiable non-linear modules that can be trained by backpropagation. In this paper, we explore the possibility of building deep models based on non-differentiable modules such as decision trees. After a discussion about the mystery behind deep neural networks, particularly by contrasting them with shallow neural networks and traditional machine-learning techniques such as decision trees and boosting machines, we conjecture that the success of deep neural networks owes much to three characteristics, i.e. layer-by-layer processing, in-model feature transformation and sufficient model complexity. On one hand, our conjecture may offer inspiration for theoretical understanding of deep learning; on the other hand, to verify the conjecture, we propose an approach that generates deep forest holding these characteristics. This is a decision-tree ensemble approach, with fewer hyper-parameters than deep neural networks, and its model complexity can be automatically determined in a data-dependent way. Experiments show that its performance is quite robust to hyper-parameter settings, such that in most cases, even across different data from different domains, it is able to achieve excellent performance by using the same default setting. This study opens the door to deep learning based on non-differentiable modules without gradient-based adjustment, and exhibits the possibility of constructing deep models without backpropagation. 相似文献