A neural network model for estimating option prices

A neural network model that processes financial input data is developed to estimate the market price of options at closing. The network's ability to estimate closing prices is compared to the Black-Scholes model, the most widely used model for the pricing of options. Comparisons reveal that the mean squared error for the neural network is less than that of the Black-Scholes model in about half of the cases examined. The differences and similarities in the two modeling approaches are discussed. The neural network, which uses the same financial data as the Black-Scholes model, requires no distribution assumptions and learns the relationships between the financial input data and the option price from the historical data. The option-valuation equilibrium model of Black-Scholes determines option prices under the assumptions that prices follow a continuous time path and that the instantaneous volatility is nonstochastic.     

神经网络稳定性的交叉验证模型

根据Skutin提出的交叉验证理论,针对神经网络学习算法提出了神经网络稳定性的交叉验证模型,并选择4种应用广泛、具有代表性的神经网络作为研究对象,通过随机数据集和UCI数据集上的数据实验结果得出了BP、RBF、GRNN、ELM等4种神经网络的稳定性排序,并用统计检验方法对排序结果进行了检验。     

神经网络后门攻击研究

针对现有的神经网络后门攻击研究工作,首先介绍了神经网络后门攻击的相关概念;其次,从研究发展历程、典型工作总结、分类情况3个方面对神经网络后门攻击研究现状进行了说明;然后,对典型的后门植入策略进行了详细介绍;最后,对研究现状进行了总结并对未来的研究趋势进行了展望.     

一种改进的人工神经网络模型

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 Network,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。     

The generation of animated motion by means of a recurrent neural network

The possibility to use neural networks to guide animated motion sequences is investigated. The performance of two recurrent architectures, both derived from the cascade-correlation network, is compared. These architectures only differ in the objective function used to train the hidden units. Small differences in performance were observed, but both networks could successfully produce simple motion sequences. An animation environment was created to display arm movement and walking sequences.     

Learning in artificial neural systems

This paper presents an overview and analysis of teaming in artificial neural systems (ANSs). It begins with a general introduction to neural networks and connectionist approaches to information processing. The basis for learning in ANSs is then described and compared with classical machine learning. While similar in some ways, ANS learning deviates from tradition in its dependence on the modification of individual weights to bring about changes in a knowledge representation distributed across connections in a network. This unique form of learning is analyzed from two aspects: the selection of an appropriate network architecture for representing the problem, and the choice of a suitable learning rule capable of reproducing the desired function within the given network. The various network architectures are classified, and then identified with explicit restrictions on the types of functions they are capable of representing. The learning rules, i.e., algorithms that specify how the network weights are modified, are similarly taxonomized and, where possible, the limitations inherent to specific classes of rules are outlined.     

Design of waveguide microwave filters by means of artificial neural networks

Cylindrical post‐based waveguide filters are a relevant component of antenna feeding networks. Their synthesis performed via automatic optimization based on full‐wave analyses can be very time consuming. In this article a novel fast‐design approach based on Levy's and Moore's algorithms and an artificial neural network (ANN) architecture is presented. © 2006 Wiley Periodicals, Inc. Int J RF and Microwave CAE, 2006.     

A comparison of gradient ascent, gradient descent and genetic-algorithm-based artificial neural networks for the binary classification problem

Abstract: We compare log maximum likelihood gradient ascent, root-mean-square error minimizing gradient descent and genetic-algorithm-based artificial neural network procedures for a binary classification problem. We use simulated data and real-world data sets, and four different performance metrics of correct classification, sensitivity, specificity and reliability for our comparisons. Our experiments indicate that a genetic-algorithm-based artificial neural network that maximizes the total number of correct classifications generally fares well for the binary classification problem. However, if the training data set contains inconsistent decisions or noise then the log maximum likelihood maximizing gradient ascent may be the best classification approach to use. The root-mean-square minimizing gradient descent approach appears to overfit training data and has the lowest reliability among the approaches considered for our research. At the end of the paper, we provide a few guidelines, including computational complexity, for selection of an appropriate technique for a given binary classification problem.     

Towards the next generation of artificial neural networks for civil engineering

The purpose of this paper is to stimulate interest within the civil engineering research community for developing the next generation of applied artificial neural networks. In particular, it identifies what the next generation of these devices needs to achieve, and provides direction in terms of how their development may proceed. An analysis of the current situation indicates that progress in the development of artificial neural network applications has largely stagnated. Suggestions are made for advancing the field to the next level of sophistication and application, using genetic algorithms and related techniques. It is shown that this approach will require the design of some very sophisticated genetic coding mechanisms in order to develop the required higher-order network structures, and will utilize development mechanisms observed in nature such as growth, self-organization, and multi-stage objective functions. The capabilities of such an approach and the way in which they can be achieved are explored with reference to the problems of: (a) determining truck attributes from the strain envelopes they induce in structural members when crossing a bridge, and; (b) developing a decision support system for dynamic control of industrialized manufacturing of houses.     

Application of artificial neural network models to linear and nonlinear RF circuit modeling

Typical RF and wireless circuits comprise a large number of linear and nonlinear components. The complexity of the RF portion of a wireless system continues to increase in order to support multiple standards, multiple frequency bands, the need for higher bandwidth, and stringent adjacent channel specifications. The time required to carry out a virtual prototyping of such complex circuits and their trade‐off analysis with the baseband circuitry can be unacceptably long, because both the circuit simulation and optimization procedures can be very time consuming. Typically, one divides the task into those of designing the nonlinear elements or subcircuits that can be accurately analyzed by using RF simulators, and uses circuit level analysis for simulating the circuits at module level. In this article, we will review some approaches to modeling both the linear RF elements as well as nonlinear subcircuits (amplifiers, mixers, VCOs), and will emphasize on the application of the artificial neural networks (ANNs). Furthermore, we will demonstrate the use of the ANN to the design of RF circuits and illustrate their application to wireless types of problems of practical interest. © 2001 John Wiley & Sons, Inc. Int J RF and Microwave CAE 11: 231–247, 2001.     

Forecasting time series with a new architecture for polynomial artificial neural network

Polynomial artificial neural networks (PANN) have been shown to be powerful for forecasting nonlinear time series. The training time is small compared to the time used by other algorithms of artificial neural networks and the capacity to compute relations between the inputs and outputs represented by every term of the polynomial. In this paper a new structure of polynomial is presented that improves the performance of this type of network considering only non-integers exponents. The architecture adaptation uses genetic algorithm (GA) to find the optimal architecture for every example. Some examples of sunspots and chaotic time series are presented.     

基于神经网络-遗传算法的CT-191合成工艺优化

本文用锌粉还原N-亚硝基二苯胺的产物直接与2-甲基-4（N,N-二苄基）氨基苯甲醛缩合合成了空穴传输材料2-甲基-4（N,N-二苄基）氨基苯甲醛-1,1-二苯腙（CT-191）,采用均匀设计制定试验方案获取原始数据,应用BP人工神经网络对合成过程中工艺参数和一次产品收率的关系建立了模型,并用遗传算法进行优化得到最佳工艺条件：原料2-甲基-4-（N,N-二苄基）氨基苯甲醛：N-亚硝基二苯胺约为1：2．5,还原时间为1h,缩合时间为2h,预测收率为96．28％。验证实验的结果为95．98％．和预测值基本吻合。为化学生产工艺的优化探索了一条新途径。     

人工神经网络在ERP系统中的应用

在传统的ERP的基础上,增加专家系统模块,即基于人工神经网络技术的预测分析模块,提出了ERP和专家系统的集成管理方法,完成复杂的非线性预测,以使ERP系统智能化、自动化水平更高。该模块采用反向传输BP神经网络模型来实现,通过网络的自适应学习和训练,找出输入和输出之间的内在联系,以求解问题。利用该专家系统对汽车制造企业市场销售量进行预测,结果表明：该方法性能、实用性和通用性好。     

基于人工神经网络对sEMG信号的手势动作识别

针对利用表面肌电信号(sEMG)对手势动作的肌电信号的研究较少和sEMG信号处理过于复杂的问题,提出了利用人工神经网络和sEMG信号对人的手势动作进行识别研究,引入了MYO硬件设备对新的手势动作sEMG信号采集.利用MYO从手臂上获取每一个手势动作的sEMG信号,提取信号特征值,作为算法的训练数据和测试数据.采用人工神经网络中的反向传递神经网络算法来进行对4种不同手势动作分类,对应目标手指识别率在90.35%.研究结果可以被用来做临床诊断和生物医学的应用以及用于现代硬件的发展和更现代化的人机交互的发展.     

人工神经网络方法与聚乙烯晶体生长速度模型的研究

用结晶温度,聚乙烯分子量,聚乙烯质量分数等参数,再用人工神经网络ANN(artificial neural network)方法以建立聚乙烯晶体生长速度(lnG)的预报模型。其拟合值、预测值与实验值的相关系数分别为0．9920和0．9844,平均相对误差分别为0．3448和0．3304,结果表明,所建立的模型可以用于聚乙烯晶体生长速度的计算机预报,克服了现有物理模型和数学方程无法应用于多个变量的缺点。因此ANN可为聚合物结晶过程的定量预报提供依据,也为ANN在聚合物其他性质的预报方面提供参考。     

Printed dipole antenna design using artificial neural network modeling for RFID application

An approach to printed dipole antenna design using the artificial neural network (ANN) modeling technique is presented in this article. Three important antenna‐layout dimensions are used to capture critical input/output relationships in the ANN model. Once fully developed, the ANN model has been shown to be as accurate as an EM simulator and much more efficient computationally in antenna design optimization. © 2006 Wiley Periodicals, Inc. Int J RF and Microwave CAE, 2006.     

基于单输出型神经网络的血细胞分类研究

分别利用BP神经网络与单输出型神经网络对已经得到的血细胞特征参数进行计算,设计出分类器对血细胞进行自动分类识别。单输出型神经网络分类器与BP神经网络分类器相比,具有设计简单、收敛速度快、识别精度高且更加稳健的优点,取得了较好的应用效果。     

人工神经网络泛化问题研究综述*

从理论、方法（思想）和技术三个层次回顾了以往工作,讨论了模型复杂度、样本复杂度及两者之间关系的相关研究;在实际中,通过控制模型复杂度、调整样本等具体技术可以在一定程度上提高神经网络的泛化能力,但这些技术仍然存在一些问题没有解决。最后提出了对今后研究的展望。     

基于潜在组分配及对比学习增强的符号二值图神经网络

针对符号二值网络的节点异质性及三角形形式平衡理论不适用性的问题,提出一种基于潜在类分配及对比学习增强的符号二值图神经网络模型,其通过同质和异质双空间的互相补充来充分提取网络的隐式和显式信息。在同质空间,采用可学习的潜在组对节点进行分配并将节点看做多个潜在组的组合,然后通过训练来自动挖掘节点间的信息。在异质空间,对节点邻居进行有方向区分的注意力聚合,然后采用网络重建的互信息对比学习来引导聚合过程以获得表达能力更强的表示向量。在符号链接预测任务上与多种相关模型进行对比实验,实验结果显示所提出的模型在四个真实数据集上采用四种评价指标获取的16个评价结果中,12个评价结果可以取得最优值,验证了所提出模型的有效性。