A neural network versus Black–Scholes: a comparison of pricing and hedging performances

An Erratum has been published for this article in Journal of Forecasting 22(6‐7) 2003, 551 The Black–Scholes formula is a well‐known model for pricing and hedging derivative securities. It relies, however, on several highly questionable assumptions. This paper examines whether a neural network (MLP) can be used to find a call option pricing formula better corresponding to market prices and the properties of the underlying asset than the Black–Scholes formula. The neural network method is applied to the out‐of‐sample pricing and delta‐hedging of daily Swedish stock index call options from 1997 to 1999. The relevance of a hedge‐analysis is stressed further in this paper. As benchmarks, the Black–Scholes model with historical and implied volatility estimates are used. Comparisons reveal that the neural network models outperform the benchmarks both in pricing and hedging performances. A moving block bootstrap is used to test the statistical significance of the results. Although the neural networks are superior, the results are sometimes insignificant at the 5% level. Copyright © 2003 John Wiley & Sons, Ltd.     

基于神经网络智能天线的一种波达方向估计方法

该文提出利用径向基函数神经网络来估计无线通信中智能天线的信号到达方向．为了减少输入，利用信号相关阵的对称性质，仅考虑相关阵中的上三角或下三角的部分元素作为网络的输入量，计算量较小．计算机模拟结果表明，该方案是有效的．     

大鼠肝ADAMs种类鉴定及肝再生过程中ADAMsmRNA差异分析

以 2 / 3肝切除 (patialhepatectomy ,PH)大鼠为材料 ,利用PT -PCR技术 ,通过ADAMs通用引物初步分析了肝脏中ADAMs种类及PH后恢复 4h和 36h时ADAMsmRNA差异。结果表明 :PH后不同恢复时间ADAMsmRNA的扩增谱带没有差异 ,但扩增谱带的强弱有变化 ;cDNA克隆和测序分析表明 ,大鼠肝脏有ADAM15和ADAM 19mRNA同源序列。     

Specific anti-tumor effect induced by attenuated Salmonella typhimurium vaccine expressing extracellular region of vascular endothelial growth factor receptor 2

The purposes of this research were to study the stable expression of exogenous gene encoding therapeutic protein in attenuated Salmonella typhimurium, observe the metabolism of oral gene vaccine carried by attenuated Salmonella typhimurium in BALB/c mouse, and investigate the feasibility of prevention and treatment of tumors by the recombinant bacteria. Recombinant plasmid pcDNA3.1 VEGFR2(n1-7) was transformed into competent attenuated Salmonella typhimurium SL3261 to develop oral DNA vaccine SL3261-pcDNA3.1 VEGFR2(n1-7). To observe whether the exogenous gene can be expressed in the recombinant bacteria, PCR was performed to amplify the CMV promoter of the eukaryotic expression vector as the proof of stable expression of exogenous protein; transmission elec- tron microscopy (TEM) was applied to observe the morphology of the recombinant bacteria to confirm that the exogenous gene has no impact on the growth of the bacteria, and then BALB/c mice were immunized with the gene vaccine. After inoculation of the gene vaccine, the recombinant bacteria SL3261 could be detected in the tissues such as small intestine, colon, liver and spleen. And then, mice in each group were challenged with tumor cells. The results of animal experiment showed that tumor growth of the mice in experimental group was inhibited and survival time of immunized mice was prolonged compared with control groups. A higher lymphocyte infiltration in tumors from animals treated with DNA vaccine was observed. Immunohistochemical analysis of tumor samples revealed an en- hanced accumulation of CD8 cytotoxic T lymphocytes, as well as an increase in CD4 cells in the tumors of animals treated with the oral gene vaccine compared to tumors from control group mice. Ultrastructure of the tumor tissue showed that tumor cells in the samples of the immunized mice were well-differentiated. Our research confirmed that the exogenous gene can be stably expressed in the attenuated Salmonella typhimurium and has no impact on the growth of the recombinant bacteria; the exogenous gene can de delivered to the host by attenuated Salmonella typhimurium to produce anti-tumor effect with no obvious cytotoxity to the host. In this study, it is established that attenuated Salmonella typhimurium could be used as a vector for oral gene vaccine, and our study provided a theoretical basis for the body distribution and the metabolism of the recombinant bacteria. This strategy may provide a simple, safe and effective way for the prevention and treatment of tumors.     

螺旋霉素发酵过程动态建模的神经网络方法

对文题所述方法,根据实验数据进行仿真研究,获得了满意的结果。为高度复杂的非线性生化过程的模型化提供了一条新的途径。     

白血病小鼠模型中P53、C-myc基因表达的变化研究

探讨DNA、RNA病毒诱导小鼠发生白血病的机制。用单纯疱疹病毒Ⅱ型（HSV－2）和C型RNA病毒诱导70只昆明小鼠，光学显微镜检测HSV－2、C型病毒诱导发生白血病的成功率。正常对照组为30只昆明小鼠。免疫组化法检测HSV－2、C型病毒致瘤后P^53、G－myc基因表达的变化。70只昆明小鼠中有47只发生白血病，成功率为67．1％。47只白血病小鼠P^53、C－myc蛋白阳性表达率均比正常对照组高（P＜0．05）；23只未形成白血病的实验组小鼠P^53、C－myc蛋白阳笥表达率均与正常对照组无显差异（P＞0．05）。HSV－2、C型病毒可以通过调节P^53、C－myc基因的表达从而诱导小鼠白血病的发生。     

发酵过程混合神经网络模型及其仿真

提出了一种新型的发酵过程混合神经网络模型，该模型由非线性神经网络和线性神经网络两部分组成，由于非线性神经网络采用结构具有线形式的Flat网络，两个网络能够合并为同一表达式，并具有线性形式，可采用线性最小二乘法求解网络权值，与串联结构及串并联结构混合神经网络模型相比，该模型训练方式简单，并可方便地使用在线辨识算法。     

基于RBF网络的混沌时间序列的建模与多步预测

提出将RBF神经网络应用于混沌时间序列的建模与预测中 ,设计了一个三层RBF网络结构 ,说明了RBF网络用于混沌时间序列建模和预测时的基本性质。仿真结果表明 ,RBF网络模型对混沌时间序列有比较强的拟合能力和比较高的一步及多步预测精度。采用RBF网络进行混沌时间序列的建模和预测能够取得比其它方法好得多的效果。     

神经网络自适应滤波器在故障诊断中的应用

分析了用自适应滤波器进行故障诊断的方法．针对该方法在计算上要花费大量时间、难于完成实时诊断任务的缺点，提出了用神经网络自适应滤波器来完成故障诊断的方法．神经网络有极快的运行速度，能很好地完成实时诊断任务．