10702 工程學群 資訊工程學系

深度學習

吳尚鴻 教授

資訊工程學系
國立清華大學資訊工程學系    教授 
國立台灣大學資訊工程學系       博士

【教學】 機器學習理論、雲端資料庫、APP創業與實作
【研究】 機器學習、巨量資料處理、App 智能
  http://www.cs.nthu.edu.tw/~shwu/
【榮譽】 New Faculty Research Award, NTHU, 2015 
  Outstanding Research Award, EECS, NTHU, 2014
Outstanding Teaching Award, EECS, NTHU, 2013
IBM Ph.D. Fellowship Award, 2008 (70/575 worldwide)


News

最新公告

2023-09-26 9/13-12/27白先勇清華文學講座4-文化的記憶與重建〡台灣篇,敬邀您的熱情參與!
2023-09-26 【學習無藩籬─把清大老師帶回家!】
2023-09-26 教師備課一定要知道3件事分享報導 !
2023-09-26 【創意小學堂– 動畫懶人包立馬打造您的動畫魂!】
2023-09-26 國外各MOOCS 平台分析調查!
2023-09-26 教師備課一定要知道3件事分享報導 ! (20221101)
2023-09-26 2022年清華大學首頁故事-清華大學周志遠教授團隊勇奪SCC世界超級電腦競賽總冠軍!
2023-09-26 【敬祝各位親愛的使用者們 :母親節愉快唷!】
2023-09-26 2023年程守慶教授最新著作【數學導論】!
2023-09-26 2023年|楊佳嫻教授最新著作《以脆弱冶金》
2023-09-26 恭喜! !!數學系高淑蓉教授〡榮獲2023年全國開放教育優良課程獎!
2023-09-26 9/13-12/27白先勇清華文學講座4-文化的記憶與重建〡台灣篇,敬邀您的熱情參與!
2023-08-31 【9/5(二)14:00-17:00開放式課程系統維護通知】
2023-08-30 程守慶教授複變數函數論課程!
2023-08-14 112學年度第2學期國立清華大學傑出教學助理獲獎名單!

Syllabus

課程大綱

This class introduces the concepts and practices of deep learning. The course consists of three parts. In the first part, we give a quick introduction of classical machine learning and review some key concepts required to understand deep learning.In the second part......
 
  

Description
This class introduces the concepts and practices of deep learning. The course consists of three parts. In the first part, we give a quick introduction of classical machine learning and review some key concepts required to understand deep learning.In the second part, we discuss how deep learning differs from classical machine learning and explain why it is effective in dealing with complex problems such as the image and natural language processing. Various CNN and RNN models will becovered. In the third part, we introduce the deep reinforcement learning and its applications.This course also gives coding labs. We will use Python 3 as the main programming language throughout the course. Some popular machine learning libraries such as Scikit-learn and Tensorflow will be used and explained in detials.

 
 
 
Syllabus  
Lecture 01  
Introduction/Scientific Python 101
Lecture 02     
Linear Algebra/Data Exploration & PCA
Lecture 03
Probability & Information Theory/Decision Trees & Random Forest

Lecture 04

Numerical Optimization/Perceptron & Adaline/Regression
Lecture 05
Learning Theory & Regularization /Regularization
Lecture 06
Probabilistic Models/Logistic Regression & Metrics 
Lecture 07
Non-Parametric Methods & SVMs/SVMs & Scikit-Learn Pipelines
Lecture 08
Cross Validation & Ensembling/CV & Ensembling

Competition01  

Predicting Appropriate Response
Lecture 09
Large-Scale Machine Learning
Lecture 10
Neural Networks: Design/TensorFlow101 & Word2Vec
Lecture 11
Neural Networks: Optimization & Regularization
Lecture 12

Convolutional Neural Networks/Nuts and Bolts of Convolutional Neural Networks/Visualization and Style Transfer

Competition 02

Image Object Detection & Localization

Lecture 13

Recurrent Neural Networks/Seq2Seq Learning for Machine Translation
Competition 03 Image Caption
Lecture 14
Unsupervised Learning/Autoencoders/GANs
Competition 04 Reverse Image Caption 
Lecture 15
Semisupervised/Transfer Learning and the Future
Lecture 16
Reinforcement Learning/Q-learning
Lecture 17
Deep Reinforcement Learning/ DQN & Policy Network
Competition 05 You Draw I Draw
   
 

 

Reference Books 
Ian Goodfellow, Yoshua Bengio, Aaron Courville, Deep Learning, MIT Press, 2016, ISBN: 0387848576
Trevor Hastie, Robert Tibshirani, Jerome Friedman, The Elements of Statistical Learning: Data Mining, Inference, and Prediction, Second Edition, Springer, 2009, ISBN: 0387848576
Christopher M. Bishop, Pattern Recognition and Machine Learning, Springer, 2006, ISBN: 0387310738
Sebastian Raschka, Python Machine Learning, Packt Publishing, 2015, ISBN: 1783555130
  
 
 
 
Online Courses 
CS231n: Convolutional Neural Networks for Visual Recognition, Stanford
 CS224d: Deep Learning for Natural Language Processing, Stanford
CS 294: Deep Reinforcement Learning, Berkeley
 MIT 6.S094: Deep Learning for Self-Driving Cars, MIT
   

Keyword

關鍵字

  • 深度學習
  • Deep Learning
  • Scientific Python
  • Neural Networks
  • Numerical Optimization

Teachers

吳尚鴻 教授

Social Share

Details