機器學習已成功應用於許多現實世界的問題，目前產業界、科研領域都需要此方面人才。 這課程為基礎簡介， 對象大學部學生為主。我們以深入淺出，介紹了機器學習基礎的model、核心概念和幾個常用的深度學習，也包含數學理論間意基礎與實作，model包括線性模型、regression、非線性模型、深度前饋網絡、深度學習、CNN的演算法，為同學日後研究打下基礎。課程並說明許多實際實務應用，包含g.手寫字辨識、語音辦認、影像、EC廣告推撥。另外， 也教導pythont程式語言與TensorFlow，以此實作機器學的範例與練習。Machine learning has been successfully applied to many real-world problems, and talents in this field are currently needed in industry and scientific research. This course is a basic introduction and is mainly targeted at university students. We introduce the basic models and core concepts of machine learning and several commonly used deep learning in simple terms, as well as the implicit foundation and implementation of mathematical theory. Models include linear models, regression, nonlinear models, deep feedforward networks, and deep learning. Learn the algorithms of CNN and lay the foundation for students’ future research. The course also explains many practical applications, including g. handwriting recognition, speech recognition, imaging, and EC advertising promotion. In addition, the pythont programming language and TensorFlow are also taught to implement examples and exercises of machine learning.
PYTHON之數學基礎與實作
Mathematical foundation and implementation of PYTHON
| 評分項目 Grading Method | 配分比例 Grading percentage | 說明 Description |
|---|---|---|
| 小考一小考一 Quiz 1 |
15 | 上機 |
| 期中考期中考 midterm exam |
30 | 期中上機+期中專題各15% |
| 小考二小考二 Quiz 2 |
15 | 筆試+上機 |
| 期末考期末考 final exam |
30 | 期末上機(10%)+期末專題(20%) |
| 作業作業 Homework |
10 | 6~8次作業 |
