本文为澳大利亚邦德大学（作者：Clarence Nyap Watt Tan）的博士论文，共220页。

人工神经网络（ANN）属于人工智能（AI）方法论的范畴，近年来随着计算机技术的进步，人们对它的兴趣又重新恢复了。人工神经网络最初是用来模拟被称为神经元的脑细胞的生物学行为的，但近年来，人工神经网络被广泛应用于机场炸弹探测、子宫颈抹片癌细胞检测、信用卡交易欺诈、精神分裂症患者、心脏病、外汇预测等领域。本文利用澳大利亚的金融数据检验了ANN应用于金融领域问题的可行性。这项研究主要集中在两个特定领域：预测新南威尔士州信用合作社的困境和建立澳元/美元外汇交易系统模型。本文探讨了应用人工神经网络解决这些问题的方法，并将其结果与传统的计量经济学方法进行了比较。本章内容安排如下：人工智能和人工神经网络简介；人工神经网络入门；人工神经网络技术和统计方法；使用人工神经网络开发信用社财务困境的预警预报器；应用金融学中的人工神经网络：一个具有交易代价的外汇市场交易系统实例；结论。

Artificial Neural Networks (ANNs), whichfall under the Artificial Intelligence (AI) methodology, have enjoyed a recentrevival in interest associated with advances in computer technology. While ANNswere originally developed to model the biological behavior of brain cells callneurons, recent years have seen them applied in such diverse areas as detectingbombs in airports, cancer cells in pap smears, fraud in credit cardtransactions, schizophrenia in mental patients, heart attacks, and foreignexchange forecasting. This thesis examines the viability of applying ANNs toproblems in the finance domain using Australian financial data. The researchfocuses on two particular areas: predicting distress in credit unions of NewSouth Wales and modeling the Australian/US dollar foreign exchange tradingsystems. The thesis examines the methodologies involved in applying ANNs tothese problems as well as comparing their results with those of moreconventional econometric methods. The chapter outline is as follows: 1:Introduction to Artificial Intelligence and Artificial Neural Networks 1: AnArtificial Neural Networks’ Primer 1: The Technical and Statistical Aspects ofArtificial Neural Networks 1: Using Artificial Neural Networks to Develop AnEarly Warning Predictor for Credit Union Financial Distress 1: ApplyingArtificial Neural Networks in Finance: A Foreign Exchange Market Trading SystemExample with Transactions Costs 1: Conclusion

1. 人工智能与人工神经网络简介

2. 人工神经网络入门

3. 人工神经网络技术和统计方法

4. 利用人工神经网络建立信用社财务困境的预警预报器

5. 人工神经网络在金融中的应用：一个具有交易代价的外汇市场交易系统

6. 结论

更多精彩文章请关注公众号：