• 沒有找到結果。

96學年度商學研究所 數量方法

N/A
N/A
Protected

Academic year: 2022

Share "96學年度商學研究所 數量方法"

Copied!
1
0
0

加載中.... (立即查看全文)

全文

(1)

96 學年度商學研究所 數量方法

類神經網路(Artificial Neural Networks, ANNs)

授課教師:李天行

授課時間:星期一下午一時四十分至四時三十分 辦公室:SL 412 or SL 241

辦公室開放討論時間:星期三下午一時四十分至二時三十分or by appointment 辦公室聯絡電話:2905-2905 or 2905-2681

E-mail address:036665@mail.fju.edu.tw, mleetw@yahoo.com

課程目標:本課程將對類神經網路及其他人工智慧工具之理論及應用做一基本 之介紹。隨著資訊科技之發展、電腦軟、硬體之強力輔佐及研究變數間關係日益 複雜等因素,類神經網路及其他人工智慧工具已逐漸成為社會科學之重要研究 工具。有鑑於此,本課程將對此漸受重視工具之基本原理加以介紹,並對各種應 用問題進行討論。最後,學生除應瞭解類神經網路之相關理論外,更應培養利用 軟體實際從事資料分析之能力,此部份將透過期末實際資料之分析及報告加以 驗收,請提早著手準備。

採用之教科書:基本上由任課老師準備教材,無特定之教科書,但修課同學將 隨時收到相關papers 之 PDF 檔案,請於授課前自行閱讀完畢。

課程涵蓋章節:Difference between ANNs and traditional statistical models Introduction to artificial neural networks

Basic concepts of ANNs and preliminary models Backpropagation neural networks

Introduction to other artificial intelligence tools General model building processes

Introduction to forecasting and classification models Journal papers discussion

Qnet software demonstration

Project implementation and presentation Final wrap up

計分方式:期中考(in class, open books and notes exam)40%、期末報告 40%及課 程參與20%。

As a man sows, so shall he reap!

參考文獻

相關文件

introduction to continuum and matrix model formulation of non-critical string theory.. They typically describe strings in 1+0 or 1+1 dimensions with a

• Note that posterior variability is higher in the full Bayesian analysis, reflecting posterior uncertainty in

The differential mode of association: Understanding of traditional Chinese social structure and the behaviors of the Chinese people. Introduction to Leadership: Concepts

The closing inventory value calculated under the Absorption Costing method is higher than Marginal Costing, as fixed production costs are treated as product and costs will be carried

運用 Zuvio IRS 與台日比較文化觀點於日本文化相關課程之教學研究 Applying Zuvio IRS and Perspective on Cultural comparison between Taiwan and Japan to Teaching

Moreover, this chapter also presents the basic of the Taguchi method, artificial neural network, genetic algorithm, particle swarm optimization, soft computing and

This study aimed to establish the strength models of High-Performance Concrete (HPC) using Nonlinear Regression Analysis (NLRA), Back-Propagation Networks (BPN) and

Finally, discriminate analysis and back-propagation neural network (BPN) are applied to compare business financial crisis detecting prediction models and the accuracies.. In