| 國立中興大學教學大綱 |
| 課程名稱 | (中) 人工智能與機器學習(6115) | ||||||||
| (Eng.) Artificial Intelligence and Machine Learning | |||||||||
| 開課單位 | 科管所 | ||||||||
| 課程類別 | 必修 | 學分 | 3 | 授課教師 | 沈培輝 | ||||
| 選課單位 | 科管所 / 碩士班 | 授課使用語言 | 英文 | 英文/EMI | N | 開課學期 | 1092 | ||
| 課程簡述 | To introduce the evolution, developments, ideas, concepts and mathematical background in the theories and applications of AI and machine learning. | ||||||||
| 先修課程名稱 | 課程含自主學習 | N | |||||||
| 課程與核心能力關聯配比(%) | 課程目標之教學方法與評量方法 | |||||||||||||
| 課程目標 | 核心能力 | 配比(%) | 教學方法 | 評量方法 | ||||||||||
| 1. To understand the history and evolution of “AI” and “machine learning”. 2. To introduce the mathematical concepts in AI, machine learning and neural networks. 3. To introduce the latest products/services which are empowered by AI, machine learning and neural networks. 4. To introduce the research groups and labs in the area of AI, machine learning and neural networks. |
|
|
|
|
||||||||||
| 授課內容(單元名稱與內容、習作/每週授課、考試進度-共18週) | ||||||||||||||
| I. Evolution of Technologies: Automation 1. Four inventions: Compass, gunpowder, paper, printing 2. Agricultural revolution 3. Steam engine (Industrial revolution) 4. Automatic control (mechanical components) 5. Electricity, electric motors, electricity supply 6. Automatic control (mechanical and electrical components) 7. Monster computers and information systems (LEO and Univac) 8. Internet 1965-1983 (Computer communication, computational resources sharing, email) 9. Personal computers and personalized systems 10. Automatic control (mechanical and electrical components equipped with programmable electronic controllers) 11. Internet and World Wide Web (Websites, application software sharing, e-commerce, cross-border information systems, Web 2.0) 12. Robots (Robotic arms, entertainment robots, humanoid robots) II. Evolution of Technologies: ICT 1. 4G LTE, 5G; WiFi, WiMax 2. Multicore CPU, RISC, ARM, Systems on Chip (SoC) 3. Case Study (SoC): Qualcomm Snapdragon 4. GPU, GPGPU, NPU, VPU, TPU 5. IBM Power processor series 6. Sensors: Accelerometer, barometer, body temperature sensor, gyroscopic sensor, heart-beat sensor, magnetometer, proximity sensor 7. Case Studies: iPhone 8 and iPhone X 8. Network (Information) security 9. Mobile devices – Notebooks, iPhone, iPad 10. Wearable devices – smartbands, iWatch, 11. Virtual reality (VR), augmented reality (AR) – HTC Vive, Google Glasses, Microsoft HoloLens 12. Personal area networks – iPhone + NBs + Headset 13. Mobile ad hoc network (MANET) – Mobile sensor network (MSN), Vehicular ad hoc network (VANET). 14. Case Studies: Google Loon and Facebook Aquila 15. Cloud: Alibaba Cloud, Amazon Cloud Service, Google Cloud Platform, IBM Cloud, Microsoft Azure, SAP Cloud Platform, Oracle Cloud, Salesforce, Tencent Cloud, Dropbox, etc. 16. Internet of Things (IoT) Cyberphysical systems (Networking of customers, manufacturers (workers and machines), R&D teams, 3PL firms (workers, machines, trucks, vessels, planes), government agencies (officers and machines), and etc.) 17. Case Study: SAP Cloud Platform 18. Case Study: Google Inc. 19. 3D printing, flying robots 20. Case Study: Walmart Robot https://www.youtube.com/watch?v=_PErP8gGli4 21. Case Study: Carrot harvesting https://www.youtube.com/watch?v=xDsZC-s6V9g 22. Case Study: Rice box production https://www.youtube.com/watch?v=NT2FZ5PbdhI 23. Case Study: Automated BMW Car Factory https://www.youtube.com/watch?v=VpwkT2zV9H0 III. AI and Machine Learning: Products and Projects 1. Intelligent agents (software robots) 2. Data mining, big data analytic and data science 3. Image/Face/Speech recognition 4. Case study: iPhone Siri 5. Case Study: Deep Learning in 11 Lines of MATLAB Code https://www.youtube.com/watch?v=-ENmRfKWjmo 6. Video: Deep Learning Research and the Future of AI – https://www.youtube.com/watch?v=5BrNt38OraE 7. Image/Language/Document/Video understanding 8. Recommender systems 9. Case studies: Amazon, Google 10. Image/Video tagging and captioning 11. Case Study: Facebook photo tagging, Google image tagging, Google Captioning Project 12. Case Study: Google Image Search, PlantSnap 13. Case Study: Google Translate, Apple QuickType 14. Sentiment analysis (Text, images, sound, video) 15. Social network analysis 16. Case Studies: IBM Deep Blue, AlphaGO 17. Case Study: IBM Watson 18. Machine vision, object recognition, target tracking, sentiment analysis 19. Case study: IBM Creates First Movie Trailer by AI for 20th Century FOX, https://www.youtube.com/watch?v=gJEzuYynaiw 20. Autonomous vehicles 21. Case Study: Automated guided vehicles (AGV) https://www.youtube.com/watch?v=dAXdeqcHBp4 (Amazon Fulfillment Center), https://www.youtube.com/watch?v=UtBa9yVZBJM (Amazon Warehouse), https://www.youtube.com/watch?v=FBl4Y55V2Z4 (Alibaba warehouse robots). 22. Case Study: Autonomous trucks, Intelligent Autopilot System 23. Brain machine interface – Engineering brain-computer interfaces to regain control of movement https://www.youtube.com/watch?v=ZpTgdQEJc6I 24. Integrating Brain-Computer Interface Technology with Augmented and Virtual Reality. Paul Sajda, https://www.youtube.com/watch?v=fn9eBJFvSuA 25. Probabilistic processors 26. AI/NN Chips Apple “Neural Engine” in A11 Bionic (should be for deep learning) Apple “Image Signal Processing Unit” (ISP) in A11 Bionic Huawei “Neural Processing Unit” (NPU) in Kirin 970 (deep learning) Google on-device AI “Federated Learning” Google “Tensor Processing Unit” (TPU) IBM TrueNorth Chip (Spike NN, 1 million neurons and 256 million synapses) Intel Movidius Myriad “Vision Processing Unit” (VPU) Intel Nervana Neural Network Processor family (previous codename Lake Crest, deep learning) Nvidia “Graphic Processing Unit” (GPU), deep learning accelerator. IV. AI & Machine Learning – Fundamental Concepts Problems Games Object recognition Language understanding Automated control Models for solving problems Biological inspired Neural networks Spike neural networks Rule-based Expert systems Fuzzy systems Statistical Models Structure equation models Latent variables model Generalized mixture models Hybrid models Extreme Learning Machine Liquid State Machine Convolution Neural Networks Diagrams for the model structures Performance measures Win/Loss Classification rate Mean squared error (MSE) Likelihood, etc. Learning – Supervised, Unsupervised, Hybrid V. AI & Machine Learning – Neural Networks and Learning Systems Fixed-Structure-and-Weights Networks Hopfield Network, Brain-State-in-a-Box (BSB) Network, Lagrange Program Neural Network, k-Winners-Take-All (kWTA) Unsupervised Learning NN Associative Network, Bidirection Associative Network (BAM) Kohonen Map (Self-Organizing Map) Supervised Learning NN Multilayer Perceptron, Radial Basis Function (RBF) Network Recurrent Neural Networks Learning Systems Gaussian Mixture Model, Independent Component Analysis (ICA) Support Vector Machine (SVM), Boltzmann Machine Restrictive Boltzmann Machine, Belief Network Learning Objectives Learning algorithms Gradient descent, Newton Method, Gradient-Free Method Simulated Annealing, Genetic Algorithm Framework – NN/LS Model + Learning Objective + Learning Algorithm VI. AI & Machine Learning – Deep Learning Models of deep neural networks Deep Belief Network, Deep Boltzmann Machine Autoencoder, Convolution Neural Network Deep XYZ Network Applications of deep neural networks Image/Video Tagging, Sentiment Analysis Voice recognition, Speech Recognition Deep learning Phase I: Layer-wise unsupervised learning Phase II: Backpropagation with/without drop out or scaling mixture Computation complexity Accelerators Apple “Neural Engine” in A11 Bionic Huawei “Neural Processing Unit” (NPU) in Kirin 970 IBM TrueNorth Chip Nvidia “Graphic Processing Unit” (GPU) Limitations VII. AI and Machine Learning: Research Labs & Developer Platforms The following list focuses more on the areas of ICT and AI. For other technologies, like autonomous cars and robotic research, you should search over the Internet for information. 1. Alibaba Cloud (Aliyun) Developer Platform, Alibaba Research Center For Complexity Sciences 2. Amazon Research Center, Amazon Lab 126 https://www.lab126.com, Amazon Developer Platform 3. Apple Machine Learning Journal, Apple Developer Program 4. Baidu Research Institute, Baidu Developer Platform 5. Cisco Research Center, Cisco Devnet 6. Facebook Research, Facebook Developer Platform 7. Google Research, Google Developer Platform 8. IBM Research, IBM developerWorks 9. Microsoft Research, Microsoft Developer Network 10. Oracle Labs, Oracle Developer Platform 11. Qualcomm Research, Qualcomm Developer Network 12. SAP Innovation Center Network, SAP Developer Center 13. Tencent Cloud 14. Tencent AI Lab (Theoretical research) 15. Tencent YouTu Lab (Applications) |
||||||||||||||
| 學習評量方式 | ||||||||||||||
| 1. Group assignments (10%) 2. Group project (20%) 3. Mid-term exam (30%) 4. Final exam (40%) |
||||||||||||||
| 教科書＆參考書目(書名、作者、書局、代理商、說明) | ||||||||||||||
| 1. Michael A. Arbib, The Metaphorical Brain 2: Neural Networks and Beyond, Wiley-Interscience, 1989. 2. Yoshua Bengio, Learning deep architectures for AI. Foundations and trends® in Machine Learning. 15;2(1):1-27, November 2009. 3. Patricia S. Churchland, and Terrence J. Sejnowski, The Computational Brain, MIT Press, 1992. 4. Gerald M. Edelman, Bright Air, Brilliant Fire: On the Matter of the Mind, Penguin, London, 1992. 5. Friedrich A. von Hayek, The Sensory Order: An Inquiry into the Foundations of Theoretical Psychology, Routledge & Kegan Raul, London, 1952. 6. Simon Haykin, Neural Networks and Learning Machines. 3rd Edition. Upper Saddle River, NJ, USA, Pearson, 2009. 7. Donald Hebb, The Organization of Behavior, New York: Wiley & Sons, 1949. 8. John McCarthy, Concepts of Logical AI, downloaded from John McCarthy Homepage, 2000. 9. Marvin Minsky, The Society of Mind, Touchstone Book, by Simon & Schuster Inc., 1986. 10. John von Neumann, The Computer and the Brain, Yale University Press, 1958. 11. Jean Piaget, The Psychology of Intelligence, Routledge, London, 1950. 12. Stuart Russell, and Peter Norvig, Artificial Intelligence: A Modern Approach, 2nd Edition, Prentice Hall, 2003. 13. Fei-Yue Wang, AI’s Hall of Frame, IEEE Intelligent Systems |
||||||||||||||
| 課程教材（教師個人網址請列在本校內之網址） | ||||||||||||||
| NA | ||||||||||||||
| 課程輔導時間 | ||||||||||||||
| Friday: 17:00-18:00 | ||||||||||||||
| 聯合國全球永續發展目標(連結網址) | ||||||||||||||
| ||||||||||||||
| 請尊重智慧財產權及性別平等意識，不得非法影印他人著作。 | |
| 更新日期 西元年/月/日：無 | 列印日期 西元年/月/日：2025 / 6 / 27 |
| MyTB教科書訂購平台：http://www.mytb.com.tw/ | |