教學大綱表 (113學年度 第1學期)
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

No.
單元主題
Unit topic
內容綱要
Content summary
1 Neural network introduction and development 1. Machine learning and the development history.
2. The core of this course
Understanding the trend and core of neural network 講授
From machine learning to Deep Learning從機器學習到深度學習的介紹  
2 Adline/madline model 及Widraw-Hoff Learning Basis of neural network and The installation of Tenserflow and keras 1. basic learning algorithms
2. installation of Tensorflow and Keras
講授
1st lab: F to C 第一個實驗之(a): 華氏對攝氏溫度之轉換 (a): 熟習 Anaconda  
3 Adline/madline and Backpagation Learning Rule 1)Widrow learning
2)Multi-layer Perceptron
3) Backpagation Learning Rule
Neural network= architecture + learning rule 講授
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 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 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
Combined learnig algorithm of VAE: Reconstruction loss + KL divergence 上機實習
講授
閱讀討論
實驗
 
8 Midterm Midterm Midterm  
9 AE. VAE. PCA Difference among AE, VAE and PCA Difference between AE VAE and PCA case studies  
10 Convolutional Neural network 1. Simple sensor makes contribution to visual intellengence.
2. CNN architecture
3. Examples demo.
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
1) Learning through BPTT
2) Gradient Varnished
上機實習
講授
個案研究
實驗
 
12 Support vector machine Margin/support vector Margin/support vector 實驗四 以LSTM自動生成音樂  
13 Generator and Adversarial Neural Network(GAN) architecture and learning rule of GAN architecture and learning rule of GAN  
14 Reinforcement learning 1.reinforcement learning
2. Q learning
3. TD Q learning
4. Deep Reinforcement Learning
basic theorem and applications  
15 Transformer basic and architecture basic and architecture  
16 Final exam final exam final exam  
17 彈性教學 Final project competion Final project competion Final project competion 彈性教學  
18 彈性教學:Reinforcement Learning Project 熟習 open-AI Gym 建立Flappy Bird遊戲 彈性教學  
彈性教學週活動規劃

No.
實施期間
Period
實施方式
Content
教學說明
Teaching instructions
彈性教學評量方式
Evaluation
備註
Notes
1 起:2024-01-01 迄:2024-01-12 5.小專題 Project Applications of LLM or TrAnsformer 創意 及完整度


教學要點概述:
1.自編教材 Handout by Instructor:
■ 1-1.簡報 Slids
■ 1-2.影音教材 Videos
□ 1-3.教具 Teaching Aids
□ 1-4.教科書 Textbook
■ 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:30%   彈性教學:10%  

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:https://curri.ttu.edu.tw/p/412-1033-1254.php