教學大綱表 Syllabus
請遵守智慧財產權,勿使用非法影印教科書,避免觸法。
課程名稱
Course Title
(中文) 類神經網路概論
(英文) Introduction To Neural Networks
開課單位
Departments
資訊工程學系
課程代碼
Course No.
I4850
授課教師
Instructor
許超雲
學分數
Credit
3.0 必/選修
core required/optional
選修 開課年級
Level
大四
先修科目或先備能力Course Pre-requisites:
課程概述與目標 Course Overview and Goals: 建立基本機器 學習之基礎及未來研究之能力
教科書
Textbook
自編講義
參考教材
Reference
每個課題之 講義均有列參考教材
課程大綱
Syllabus
學生學習目標
Learning Objectives
單元學習活動
Learning Activities
學習成效評量
Evaluation
備註
Notes

Week
單元主題
Unit topic
內容綱要
Content summary
1 Neural network 簡介及應用: 1. 機器學習, 神經網路之沿起歷史.
2. 機器學習之重要運用
了解類神經系統重要
  • 討論
  • 講授
  • 從機器學習到深度學習的介紹  
    2 Adline/madline model 及Widraw-Hoff Learning 基礎/理論課程授課及Tenserflow及keras入手 1. basic learning algorithms
    2. tensorflow 及 Keras 安裝入手
  • 討論
  • 講授
  • 實驗Experiment
  • 第一個實驗之(a): 華氏對攝氏溫度之轉換 (a): 熟習 Anaconda  
    3 Adline/madline及Backpagation Learning Rule 1)Widrow learning
    2)Multi-layer Perceptron
    3) Backpagation Learning Rule
    Neural network= architecture + learning rule
  • 討論
  • 講授
  • 實驗Experiment
  • 第一個實驗之(a): 華氏對攝氏溫度之轉換: 程式試RUN及修改  
    4 introduction to backprogation BP Architecture and learning Rule Architcture and learning rule  
    5 Complexity of machine learning Optimizer and Loss function for machine learning The complexity of learning and related performance index
  • 討論
  • 講授
  • 實驗Experiment
  • 第一個實驗之(b)): 華氏對攝氏溫度之轉換以MLP+BP方式實現  
    6 Introduction to Autoencoder(AE) 1.Autoencoder= Encoder + Decoder without Supervision
    2. PCA Vs. Autoencoder
    3. Laternal space
    AE' s adavantage and Bottleneck
  • 討論
  • 講授
  • 實驗Experiment
  • 實驗二以自編碼器(AE)實現MNIST資料庫手寫數字之資料降維  
    7 Variational Autoencoder (VAE) 1) 4 disadvantages of AE
    2) VariationalAE
    3) Crossentropy Vs. KL Diveregence
    4) Random generator
    Improve learnig algorithm and Architecture of BP
  • 討論
  • 講授
  • 模擬期中考  
    8 AE. VAE. PCA Difference between AE VAE and PCA Difference between AE VAE and PCA
  • 討論
  • 上機實習
  •  
    9 Midterm Midterm Midterm  
    10 Convolutional Neural network 1. Simple sensor makes contribution to visual intellengence.
    2. CNN architecture
    3. Examples demo.
    Architecture and learning rule of CNN
  • 討論
  • 講授
  • 實驗Experiment
  • 實驗三 以變分自編碼器(VAE)實現 MNIST資料降維分析與產生測試  
    11 Self-organizing Feature map Architecture and learning Rule for SOFM Architecture and learning Rule for SOFM  
    12 Feedback NN 1) RNN
    2) LSTM
    The architecture and Learning rule of RNN and LSTM
  • 討論
  • 講授
  • Final Project proposal  
    13 Support vector machine Margin/support vector Margin/support vector
  • 討論
  • 講授
  • 實驗Experiment
  • 實驗四 以LSTM自動生成音樂  
    14 Generator and Adversarial Neural Network(GAN) architecture and learning rule of GAN architecture and learning rule of GAN
  • 討論
  • 講授
  •  
    15 Reinforcement learning 1.reinforcement learning
    2. Q learning
    3. TD Q learning
    4. Deep Reinforcement Learning
    basic theorem and applications
  • 討論
  • 講授
  • 實驗Experiment
  • 實驗五: Q learning  
    16 Transformer basic and architecture basic and architecture
  • 討論
  • 講授
  •  
    17 report of Final project final project report final project report
  • 個案研究
  • 實驗Experiment
  • 每人一組報告  
    18 Final project competion Final project competion Final project competion
  • 心得發表
  • 期末考Final Exam
  • 實驗Experiment
  •  

    教學要點概述 Overview of Teaching Points:
    教材編選 Teaching Materials: ■ 自編教材 Handout by Instructor □ 教科書作者提供 Textbook
    評量方法 Evaluation: 期末考Final Exam:30%   期中考Midterm:30%   實驗Experiment:40%  
    教學資源 Teaching Resources: ■ 教材電子檔 Soft Copy of the Handout or the Textbook □ 課程網站 Website
    扣考規定 The rule of being able to take the final exam of the course:http://eboard.ttu.edu.tw/ttuwebpost/showcontent-news.php?id=504