課程名稱Course Title (中文) 類神經系統 (英文) Artificial Neural Systems And Laboratory 開課單位Departments 電機工程研究所 課程代碼Course No. E5770B 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 研究所 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 學習之基礎應用及研究之能力 教科書(Textbook) 參考教材(Reference)
 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 序No. 單元主題Unit topic 內容綱要Content summary 1 Neural network 簡介 1.神經網路歷史 2.神經網路數位模式: P erceptron model 對神經網路的模式: 輸入之加權, 輸出及加權調整有概念 2 Adline/madline model 及Widraw-Hoff Learning 1. 學習法則之基礎/理論課程授課 2 Tenserflow及keras入手 1. basic learning algorithms 2. tensorflow 及 Keras 安裝入手 第一個實驗之(a): 攝氏對華氏溫度之轉換 (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 第一個實驗之(a):攝氏對華氏溫度之轉換: 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 第一個實驗之(b)): 攝氏對華氏溫度之轉換以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 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 AE 's basic and learning algorithm 模擬期中考 8 AE. VAE. and PCA Difference between AE VAE and PCA Difference between AE VAE and PCA 9 Midterm exam Midterm exam Midterm Exam 10 Convolutional Neural network 1. Simple sensor makes contribution to visual intellengence. 2. CNN　architecture 3. Examples . Architecture and learning rule of CNN 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 Feedback NN 1) RNN 2) LSTM The architecture and Learning rule of RNN and LSTM Final Project proposal 12 Support vector machine Margin/support vector Margin/support vector 實驗四 以LSTM自動生成音樂 13 Generative and Adversarial Neural Network(GAN) architecture and learning rule of GAN architecture and learning rule of GAN 14 Reinforcement learning(RL) 1.reinforcement learning 2. Q learning 3. TD Q learning 4. Deep Reinforcement Learning basic theorem of RL and applications 實驗五: Q learning 15 Transformer basis and architecture basis and architecture 16 Restricted Boltzman Machine 1. RBM　architecture 2. Learning rule RBM learning rule and architecture 17 Report on Final project Report final project project present 18 Final Exam Final Exam Final Exam

 教學要點概述： 教材編選(Teaching Materials)： □ 1-1.簡報 Slids □ 1-2.影音教材 Videos □ 1-3.教具 Teaching Aids □ 1-4.教科書 Textbook Slids □ 1-5.其他 Other □ 2.自編評量工具/量表 Educational Assessment □ 3.教科書作者提供 Textbook 成績考核 Performance Evaluation： 期末考：30%   期中考：30%   實驗：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：http://eboard.ttu.edu.tw/ttuwebpost/showcontent-news.php?id=504