課程大綱

課程資訊

課程名稱	系統效能評估 Performance Modeling
開課學期	109-2
授課對象	電機資訊學院資訊工程學研究所
授課教師	周承復
課號	CSIE5023
課程識別碼	922 U0240
班次
學分	3.0
全/半年	半年
必/選修	選修
上課時間	星期一7,8,9(14:20~17:20)
上課地點
備註	上課教室：資310。總人數上限：30人
Ceiba 課程網頁	http://ceiba.ntu.edu.tw/1092CSIE5023_
課程簡介影片
核心能力關聯	核心能力與課程規劃關聯圖
課程大綱
為確保您我的權利,請尊重智慧財產權及不得非法影印
課程概述	Performance Modeling: Distributed Machine-Learning System is an introduction to these system-focused aspects of machine learning, covering guiding principles and commonly used techniques for scaling up to large data sets. That is, we will cover the techniques that lie between a standard machine learning course and an efficient systems implementation. Overview of SGD SGD The condition number The kernel trick Non-convex stochastic gradient descent Parallelism Algorithms other than SGD MDP and Reinforcement Learning Policy gradient, DDPG NAS Hybrid types of learning Broad techniques Online versus offline learning Metaparameter optimization
課程目標	Performance Modeling: Distributed Machine-Learning System is an introduction to these system-focused aspects of machine learning, covering guiding principles and commonly used techniques for scaling up to large data sets.
課程要求	Basic ML and Programming knowledge Math/Statistics knowledge
預期每週課後學習時數
Office Hours
指定閱讀	papers and slides
參考書目	papers
評量方式 (僅供參考)

課程進度

週次	日期	單元主題
第1週	2/20	Introduction
第2週	2/27	Holiday
第3週	3/06	Overview
第4週	3/13	Overview
第5週	3/20	Techniques for SGD
第6週	3/27	Techniques for SGD
第7週	4/03	Holiday
第8週	4/10	Variance Reduction in SGD
第9週	4/17	The Kernel Trick, Gram Matrices, and Feature Extraction
第10週	4/24	sample of mid-term exam paper list
第11週	5/01	Midterm
第12週	5/10	Hyperparameter Optimization, Parallelism
第13週	5/17	Markov Decision Process and Reinforcement Learning
第14週	5/22	Paper Presentation 1 吳禹璇 Privacy-Preserving Traffic Flow Prediction: A Federated Learning Approach https://youtu.be/dwGzcLuv1tQ 2 黃光輝 When Edge Meets Learning: Adaptive Control for Resource-Constrained Distributed Machine Learning https://youtu.be/RxU0kCTRc7g 3 彭梓瑄 Federated Learning with Matched Averaging https://www.youtube.com/watch?v=JjLONixIZd4 4 許宛筑 Human-level control through deep reinforcement learning https://youtu.be/pbzhttrIEWM
第15週	5/29	Paper Presentation 1 陳俊瑋 Policy Gradient Methods for Reinforcement Learning with Function Approximation https://www.youtube.com/watch?v=cbDXk4OpTCw 2 鍾宜樺 Variational Neural Annealing https://www.youtube.com/watch?v=qnIGt29Jrx8 3 謝宏祺 A Closer Look at Few-shot Classification https://youtu.be/bT0X-1rIptM 4 吳旻栗 "Scalable Distributed DL Training: Batching Communication and Computation https://drive.google.com/file/d/1l7SI2aSuaZ2q4Iyt60t1y233LMwxdAnu/view
第16週	6/05	Paper Presentation 1 許國讚 A Survey of Actor-Critic Reinforcement Learning: Standard and Natural Policy Gradient 2 蘇泰宇 HOGWILD! A Lock-Free Approach to Parallelizing Stochastic Gradient Descent https://www.youtube.com/watch?v=Tl7S2UHrif8&ab_channel=%E8%98%87%E6%B3%B0%E5%AE%87 3 楊晨郁 Metagan: An adversarial approach to few-shot learning https://youtu.be/MydqE2KB64s
第17週	6/12	Paper Presentation 1 李岳庭 Optimization as a model for few-shot learning 2 徐衍新 Model-agnostic meta-learning for fast adaptation of deep networks https://youtu.be/c47HrCB4pgw 3 吳吉加 Mastering the game of Go with deep neural networks and tree search
第18週	06/19	Final Project Presentation https://docs.google.com/spreadsheets/d/15FcYhry41osPT9EBYnP9eHkVXJk7gHblFmfRELDwuwg/edit?usp=sharing