傳統計算的主要特徵是嚴格、確定和精確，但其並不適合處理現實生活中的許多問題，例如駕駛汽車、下棋、家電控制…等。但軟式計算基於其不確定、不精確及不完全真值的容錯特性，可提供低成本的方案解決許多日常生活中的問題。本課程將介紹軟式計算的基本原理、相關計算模式，及其在人工智慧與機器學習領域的應用。本課程將介紹的軟式計算的計算模式主要包括了: Neural networks、fuzzy logic、evolutionary computation、simulated annealing、swarm intelligence…等。此外，由於人工智慧及大數據分析技術在商業領域的應用越來越頻繁而重要，本課程將著重介紹資料科學在行銷領域的應用，包含了關鍵績效指標與視覺化、行銷參與度背後的驅動因素、參與度與轉換率間的關係、產品可見度與行銷、個人化行銷、產生更好的行銷決策...等。本課程所介紹的行銷資料科學案例，均可使用 R 及 Python 進行實作，以協助學生將課堂所學應用在實際的場合上。The main characteristics of traditional calculations are strict, accurate and accurate, but they are not suitable for dealing with many problems in real life, such as driving cars, playing chess, home appliance control... etc. However, based on its inaccurate, inaccurate and incomplete true value, soft calculation can provide low-cost solutions to solve many problems in daily life. This course will introduce the basic principles, related computing modes, and its application in the fields of artificial intelligence and machine learning. The calculation modes of soft computing introduced in this course mainly include: Neural networks, fuzzy logic, evolutionary computing, simulated annealing, swarm intelligence, etc. In addition, as artificial intelligence and large data analysis technology are becoming increasingly complex and important in the business field, this course will focus on introducing the application of data science in the marketing field, including the driving force behind key performance indicators and visualization, marketing participation Factors, relationships between participation and conversion rates, product visibility and marketing, personalized marketing, resulting in better marketing decisions... etc. All marketing data science cases introduced in this course can be implemented in R and Python to help students apply the lessons to their actual situation.
1. Yoon-Hyup Hwang, Hands-On Data Science for Marketing, Packt Publishing Limited., March 2019.
2. Sebastian Raschka, Vahid Mirjalili, Python Machine Learning: Machine Learning and Deep Learning with Python, scikit-learn, and TensorFlow, 2nd Edition, Packt Publishing Limited., September 2017.
3. Prateek Joshi, Artificial Intelligence with Python, Packt Publishing Limited., January 2017.
1. Yoon-Hyup Hwang, Hands-On Data Science for Marketing, Packt Publishing Limited., March 2019.
2. Sebastian Raschka, Vahid Mirjalili, Python Machine Learning: Machine Learning and Deep Learning with Python, scikit-learn, and TensorFlow, 2nd Edition, Packt Publishing Limited., September 2017.
3. Prateek Joshi, Artificial Intelligence with Python, Packt Publishing Limited., January 2017.
| 評分項目 Grading Method | 配分比例 Grading percentage | 說明 Description |
|---|---|---|
| 課堂參與課堂參與 Class Participation |
15 | |
| 課堂作業課堂作業 Classroom Works |
35 | |
| 期中考期中考 Midterm exam |
25 | |
| 期末專題期末專題 Final topics |
25 |
