Advanced Machine Learning Lecture Notes PDF

10/21/2024 Advanced Machine Learning Dr.Mohamed Moustafa Associate Professor , Computers and Artificial Intelligence CIO – DMU,SAS,MS 1 Class Rules You can do anything except: Make noises (chatting, singing…)...

10/21/2024 Advanced Machine Learning Dr.Mohamed Moustafa Associate Professor , Computers and Artificial Intelligence CIO – DMU,SAS,MS 1 Class Rules You can do anything except: Make noises (chatting, singing…) Feel free to interrupt me if you have questions. According to the university policy,taking attendance is needed. Important: you are required to have an 80% attendance to be able to seat for the final exam. 2 2 1  10/21/2024 Course Assessment  Temporary according to the situation:  Final exam:50%  Assignment:20%,individually  Project:30%,2-3 members per group,report and presentation are required.  Important:cheating and plagiarism will get no marks. 3 A few suggestions…. Your final grade is based on points – not on an accumulation of grades. You start the class with zero points and earn your way to your final grade If you have an issue or problem, communicate – send me an email If you know you’re not going to meet the deadline for a quiz or assignment – email me BEFORE the deadline 4 4 2  10/21/2024 Data challenges … Agenda “Data Everywhere, You have data , You have Everything ” 5 DATA INTELLIGENCE 6 3  10/21/2024 7 Why analytics ? 8 4  10/21/2024 Why analytics ? 9 Levels of Analytics 10 C o p y r i ght © S A S I n s titu te In c. A ll r igh ts r e s e r v e d. 10 5  10/21/2024 ANALYTICS C o p yr ig h t © S A S I n s t it u t e I n c. A ll r i g h t s r e s e rved. 11 C o p yr ig h t © S A S I n s t it u t e I n c. A ll r i g h t s r e s e rved. 12 6  10/21/2024 Analytics is core to success in the digital economy. Data and analytics driven organizations will thrive. Chandana Gopal, IDC, December 2017 C o p yr ig h t © S A S I n s t it u t e I n c. A ll r i g h t s r e s e rved. 13 ARTIFICIAL INTELLIGENCE 1. © 2020 GEOCODE 14 7  10/21/2024 What is AI? AI can be broadly defined as technology that can learn and produce intelligent behavior Input Output Pixels: An AI Process “Tuberculosis” Computer Vision 15 But, What is AI? AI can be broadly defined as technology that can learn and produce intelligent behavior Input Output “Four kids are playing Pixels: An AI Process with a ball” More than just a category Computer Vision about the image! 16 8  10/21/2024 But, What is AI? AI can be broadly defined as technology that can learn and produce intelligent behavior Input Output Audio Clip: An AI Process “I feel some eye pain” Speech Recognition 17 But, What is AI? AI can be broadly defined as technology that can learn and produce intelligent behavior Input Output Text: “Hello, how are you?” An AI Process “Bonjour, comment allez-vous” Machine Translation 18 9  10/21/2024 ARTIFICIAL INTELLIGENCE Eras 19 ARTIFICIAL INTELLIGENCE Eras 20 10  10/21/2024 Machine learning Human Machine VS learning learning Learn from experience 21 Machine learning Human Machine VS learning learning Learn from Historical data 22 11  10/21/2024 Machine learning 23 Classification 24 12  10/21/2024 Clustering 25 Dimensionality Reduction 26 13  10/21/2024 Graph Analysis 27 Graph Analysis 28 14  10/21/2024 Natural Language processing (NLP) Chatbot 29 ARTIFICIAL INTELLIGENCE Eras 30 15  10/21/2024 Computer Vision Object classification Object identification Scene reconstruction Motion analysis 31 Computer Vision Object classification Object identification © 2020 GEOCODE 32 16  10/21/2024 Computer Vision 33 Human Visual 34 17  10/21/2024 35 36 18  10/21/2024 37 Computer Vision Theoretical and algorithm basic to achieve automatic visual understanding High-level understanding from digital image or video Computer vision aims to come up with computational model of the human visual system Computer vision aims to build autonomous systems to perform some of the tasks which the human visual system can perform and even surpass it in many cases 38 19  10/21/2024 39 Examples of computer vision algorithms and applications 40 20  10/21/2024 Examples of computer vision algorithms and applications 41 Examples of computer vision algorithms and applications 42 21  10/21/2024 Examples of computer vision algorithms and applications 43 Every image tells a story Goal of computer vision: perceive the “story” behind the picture Compute properties of the world 3D shape Names of people or objects What happened? 44 22  10/21/2024 Can computers match human perception? Yes and no (mainly no) computers can be better at “easy” things humans are better at “hard” things But huge progress Accelerating in the last five years due to deep learning What is considered “hard” keeps changing 45 The goal of computer vision 46 23  10/21/2024 The goal of computer vision Compute the 3D shape of the world ZED 2i Camera 47 The goal of computer vision Recognize objects and people Terminator 2, 1991 48 24  10/21/2024 slide credit: Fei-Fei, Fergus & Torralba 49 sky building flag face banner wall street lamp bus bus cars slide credit: Fei-Fei, Fergus & Torralba 50 25  10/21/2024 The goal of computer vision “Enhance” images 51 52 26  10/21/2024 The goal of computer vision Forensics Source: Nayar and Nishino, “Eyes for Relighting” 53 Source: Nayar and Nishino, “Eyes for Relighting” 54 27  10/21/2024 Source: Nayar and Nishino, “Eyes for Relighting” 55 The goal of computer vision Improve photos (“Computational Photography”) Super-resolution (source: 2d3) Depth of field on cell phone camera (source: Google Research Blog) Removing objects (Google Magic Eraser) Low-light photography (credit: Hasinoff et al., SIGGRAPH ASIA 2016) 56 28  10/21/2024 Digital Image Processing Image to image Transformation Image Compression Image restoration Image enhancement 57 Machine Vision Applying a range of technologies and methods, including imaging-based automatic observation and process control 58 29  10/21/2024 Computer Graphics and Computer Vision Image-based rendering Image morphing View interpolation Panoramic image stitching Early light-field rendering 59 30