Lecture 1: Introduction - Stanford Artificial Intelligence Laboratory
Lecture 1:IntroductionFei-Fei Li & Andrej Karpathy & Justin JohnsonLecture 1 -14-Jan-16
Welcome to CS231nFei-Fei Li & Andrej Karpathy & Justin JohnsonLecture 1 -24-Jan-16
cesopticsImageprocessingComputerVisionSpeech, NLPEngineeringRoboticsgraphics, algorithms,theory, ComputerSciencesystems,architecture, Information retrievalMachine learningMathematicsFei-Fei Li & Andrej Karpathy & Justin JohnsonLecture 1 -34-Jan-16
cesopticsImageprocessingComputerVisionSpeech, NLPEngineeringRoboticsgraphics, algorithms,theory, ComputerSciencesystems,architecture, Information retrievalMachine learningMathematicsFei-Fei Li & Andrej Karpathy & Justin JohnsonLecture 1 -44-Jan-16
Computer Vision courses @ Stanford CS131 (fall, 2015, Profs. Fei-Fei Li & Juan CarlosNiebles):– Undergraduate introductory class CS231a (spring term, Prof. Silvio Savarese)– Core computer vision class for seniors, masters, andPhDs– Topics include image processing, cameras, 3Dreconstruction, segmentation, object recognition,scene understanding CS231n (this term, Prof. Fei-Fei Li & AndrejKarpathy & Justin Johnson)– Neural network (aka “deep learning”) class onimage classification And an assortment of CS331 and CS431 foradvanced topics in computer visionFei-Fei Li & Andrej Karpathy & Justin JohnsonLecture 1 -54-Jan-16
Today’s agenda A brief history of computer vision CS231n overviewFei-Fei Li & Andrej Karpathy & Justin JohnsonLecture 1 -64-Jan-16
543million years, B.C.Fei-Fei Li & Andrej Karpathy & Justin JohnsonLecture 1 -74-Jan-16
CameraObscuraLeonardo da Vinci16th Century, A.D.Fei-Fei Li & Andrej Karpathy & Justin JohnsonLecture 1 -84-Jan-16
Hubel & Wiesel, 1959Fei-Fei Li & Andrej Karpathy & Justin JohnsonLecture 1 -94-Jan-16
BlockworldLarry Roberts,1963Fei-Fei Li & Andrej Karpathy & Justin JohnsonLecture 1 -104-Jan-16
Fei-Fei Li & Andrej Karpathy & Justin JohnsonLecture 1 -114-Jan-16
David Marr, 1970sFei-Fei Li & Andrej Karpathy & Justin JohnsonLecture 1 -124-Jan-16
Stages of Visual Representation, David Marr,1970sFei-Fei Li & Andrej Karpathy & Justin JohnsonLecture 1 -134-Jan-16
Generalized CylinderBrooks & Binford, 1979Fei-Fei Li & Andrej Karpathy & Justin Johnson Pictorial StructureFischler and Elschlager, 1973Lecture 1 -144-Jan-16
David Lowe, 1987Fei-Fei Li & Andrej Karpathy & Justin JohnsonLecture 1 -154-Jan-16
Normalized Cut(Shi & Malik, 1997)Fei-Fei Li & Andrej Karpathy & Justin JohnsonLecture 1 -164-Jan-16
Face Detection, Viola & Jones, 2001Fei-Fei Li & Andrej Karpathy & Justin JohnsonLecture 1 -174-Jan-16
“SIFT” & Object Recognition, David Lowe, 1999Fei-Fei Li & Andrej Karpathy & Justin JohnsonLecture 1 -184-Jan-16
Spatial Pyramid Matching, Lazebnik, Schmid & Ponce, 2006Fei-Fei Li & Andrej Karpathy & Justin JohnsonLecture 1 -194-Jan-16
Histogram of Gradients (HoG)Dalal & Triggs, 2005Fei-Fei Li & Andrej Karpathy & Justin JohnsonDeformable Part ModelFelzenswalb, McAllester, Ramanan,2009Lecture 1 -204-Jan-16
PASCAL Visual Object Challenge(20 object categories)[Everingham et al. dplantsheepsofatraintvmonitorAverage ge YearFei-Fei Li & Andrej Karpathy & Justin JohnsonLecture 1 -214-Jan-16
www.image-net.org22K categories and 14M images Animals Bird Fish Mammal Invertebrate Plants Tree Flower Food Materials Structures Artifact Tools Appliances Structures Person Scenes Indoor Geological Formations Sport ActivitiesDeng, Dong, Socher, Li, Li, & Fei-Fei, 2009Fei-Fei Li & Andrej Karpathy & Justin JohnsonLecture 1 -224-Jan-16
Steel drumThe Image Classification Challenge:1,000 object classes1,431,167 imagesOutput:ScaleT-shirtSteel drumDrumstickMud turtle Output:ScaleT-shirtGiant pandaDrumstickMud turtle Russakovsky et al. arXiv, 2014Fei-Fei Li & Andrej Karpathy & Justin JohnsonLecture 1 -234-Jan-16
Steel drumThe Image Classification Challenge:1,000 object classes1,431,167 images0.280.260.160.120.07Russakovsky et al. arXiv, 2014Fei-Fei Li & Andrej Karpathy & Justin JohnsonLecture 1 -244-Jan-16
Today’s agenda A brief history of computer vision CS231n overviewFei-Fei Li & Andrej Karpathy & Justin JohnsonLecture 1 -254-Jan-16
CS231n focuses on one of the most importantproblems of visual recognition –image classificationFei-Fei Li & Andrej Karpathy & Justin JohnsonLecture 1 -264-Jan-16
Fei-Fei Li & Andrej Karpathy & Justin JohnsonLecture 1 -274-Jan-16
There is a number of visual recognition problemsthat are related to image classification, such asobject detection, image captioningFei-Fei Li & Andrej Karpathy & Justin JohnsonLecture 1 -284-Jan-16
Object detection Action classification Image captioning Fei-Fei Li & Andrej Karpathy & Justin JohnsonLecture 1 -294-Jan-16
Convolutional Neural Network (CNN) hasbecome an important tool for object recognitionFei-Fei Li & Andrej Karpathy & Justin JohnsonLecture 1 -304-Jan-16
Year 2010Year 2012NEC-UIUCSuperVisionYear 2014GoogLeNetYear 2015VGGMSRADense grid descriptor:HOG, LBPCoding: local coordinate,super-vectorPooling, SPMLinear SVMConvolutionPoolingSoftmaxOther[Lin CVPR 2011][Krizhevsky NIPS 2012]Fei-Fei Li & Andrej Karpathy & Justin Johnson[Szegedy arxiv 2014][Simonyan arxiv 2014]Lecture 1 -314-Jan-16
Convolutional Neural Network (CNN)is not invented overnightFei-Fei Li & Andrej Karpathy & Justin JohnsonLecture 1 -324-Jan-16
1998LeCun et al.# of transistors106# of pixels used in training1072012Krizhevskyet al.# of transistors GPUs109Fei-Fei Li & Andrej Karpathy & Justin Johnson# of pixels used in training1014Lecture 1 -334-Jan-16
The quest for visual intelligencegoes far beyond object recognition Fei-Fei Li & Andrej Karpathy & Justin JohnsonLecture 1 -344-Jan-16
Fei-Fei Li & Andrej Karpathy & Justin JohnsonLecture 1 -354-Jan-16
Fei-Fei Li & Andrej Karpathy & Justin JohnsonLecture 1 -364-Jan-16
PT 500msSome kind of game or fight. Two groups of twomen? The foregound pair looked like one wasgetting a fist in the face. Outdoors seemed likebecause i have an impression of grass andmaybe lines on the grass? That would be why Ithink perhaps a game, rough game though,more like rugby than football because they pairsweren't in pads and helmets, though I did getthe impression of similar clothing. maybe sometrees? in the background. (Subject: SM)Fei-Fei, Iyer, Koch, Perona, JoV, 2007Fei-Fei Li & Andrej Karpathy & Justin JohnsonLecture 1 -374-Jan-16
Fei-Fei Li & Andrej Karpathy & Justin JohnsonLecture 1 -384-Jan-16
Computer VisionTechnologyCan Better Our LivesFei-Fei Li & Andrej Karpathy & Justin JohnsonLecture 1 -394-Jan-16
Who we are Instructors Teaching Assistants Keeping in touch:– cs231n-winter1516staff@lists.stanford.edu– PiazzaFei-Fei Li & Andrej Karpathy & Justin JohnsonLecture 1 -404-Jan-16
Our philosophy Thorough and Detailed.– Understand how to write from scratch, debug and trainconvolutional neural networks. Practical.– Focus on practical techniques for training these networksat scale, and on GPUs (e.g. will touch on distributedoptimization, differences between CPU vs. GPU, etc.) Alsolook at state of the art software tools such as Caffe, maybealso Torch and TensorFlow State of the art.– Most materials are new from research world in the past 1-3years. Very exciting stuff! Fun.– Some fun topics such as Image Captioning (using RNN)– Also DeepDream, NeuralStyle, etc.Fei-Fei Li & Andrej Karpathy & Justin JohnsonLecture 1 -414-Jan-16
Our philosophy (cont’d) Fun.– Some fun topics such as Image Captioning (using RNN)– Also DeepDream, NeuralStyle, etc.Fei-Fei Li & Andrej Karpathy & Justin JohnsonLecture 1 -424-Jan-16
Grading policy 3 Problem Sets: 15% x 3 45% Midterm Exam: 15% Final Course Project: 40%– Milestone: 5%– Final write-up: 35%– Bonus points for exceptional poster presentation Late policy––––7 free late days – use them in your waysAfterwards, 25% off per day lateNot accepted after 3 late days per PSDoes not apply to Final Course Project Collaboration policy– Read the student code book, understand what is ‘collaboration’and what is ‘academic infraction’Fei-Fei Li & Andrej Karpathy & Justin JohnsonLecture 1 -434-Jan-16
Pre-requisite Proficiency in Python, some high-level familiaritywith C/C – All class assignments will be in Python (and usenumpy), but some of the deep learning libraries wemay look at later in the class are written in C .– A Python tutorial available on course website College Calculus, Linear Algebra Equivalent knowledge of CS229 (MachineLearning)– We will be formulating cost functions, takingderivatives and performing optimization with gradientdescent.Fei-Fei Li & Andrej Karpathy & Justin JohnsonLecture 1 -444-Jan-16
Syllabus Go to website tmlFei-Fei Li & Andrej Karpathy & Justin JohnsonLecture 1 -454-Jan-16
References Hubel, David H., and Torsten N. Wiesel. "Receptive fields, binocular interaction and functionalarchitecture in the cat's visual cortex." The Journal of physiology 160.1 (1962): 106. [PDF]Roberts, Lawrence Gilman. "Machine Perception of Three-dimensional Solids." Diss. MassachusettsInstitute of Technology, 1963. [PDF]Marr, David. "Vision.” The MIT Press, 1982. [PDF]Brooks, Rodney A., and Creiner, Russell and Binford, Thomas O. "The ACRONYM model-based visionsystem. " In Proceedings of the 6th International Joint Conference on Artificial Intelligence (1979): 105113. [PDF]Fischler, Martin A., and Robert A. Elschlager. "The representation and matching of pictorial structures."IEEE Transactions on Computers 22.1 (1973): 67-92. [PDF]Lowe, David G., "Three-dimensional object recognition from single two-dimensional images," ArtificialIntelligence, 31, 3 (1987), pp. 355-395. [PDF]Shi, Jianbo, and Jitendra Malik. "Normalized cuts and image segmentation." Pattern Analysis andMachine Intelligence, IEEE Transactions on 22.8 (2000): 888-905. [PDF]Viola, Paul, and Michael Jones. "Rapid object detection using a boosted cascade of simple features."Computer Vision and Pattern Recognition, 2001. CVPR 2001. Proceedings of the 2001 IEEE ComputerSociety Conference on. Vol. 1. IEEE, 2001. [PDF]Lowe, David G. "Distinctive image features from scale-invariant keypoints." International Journal ofComputer Vision 60.2 (2004): 91-110. [PDF]Lazebnik, Svetlana, Cordelia Schmid, and Jean Ponce. "Beyond bags of features: Spatial pyramidmatching for recognizing natural scene categories." Computer Vision and Pattern Recognition, 2006IEEE Computer Society Conference on. Vol. 2. IEEE, 2006. [PDF]Fei-Fei Li & Andrej Karpathy & Justin JohnsonLecture 1 -464-Jan-16
Dalal, Navneet, and Bill Triggs. "Histograms of oriented gradients for human detection." Computer Visionand Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on. Vol. 1. IEEE, 2005.[PDF]Felzenszwalb, Pedro, David McAllester, and Deva Ramanan. "A discriminatively trained, multiscale,deformable part model." Computer Vision and Pattern Recognition, 2008. CVPR 2008. IEEE Conferenceon. IEEE, 2008 [PDF]Everingham, Mark, et al. "The pascal visual object classes (VOC) challenge." International Journal ofComputer Vision 88.2 (2010): 303-338. [PDF]Deng, Jia, et al. "Imagenet: A large-scale hierarchical image database." Computer Vision and PatternRecognition, 2009. CVPR 2009. IEEE Conference on. IEEE, 2009. [PDF]Russakovsky, Olga, et al. "Imagenet Large Scale Visual Recognition Challenge." arXiv:1409.0575. [PDF]Lin, Yuanqing, et al. "Large-scale image classification: fast feature extraction and SVM training."Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on. IEEE, 2011. [PDF]Krizhevsky, Alex, Ilya Sutskever, and Geoffrey E. Hinton. "Imagenet classification with deepconvolutional neural networks." Advances in neural information processing systems. 2012. [PDF]Szegedy, Christian, et al. "Going deeper with convolutions." arXiv preprint arXiv:1409.4842 (2014). [PDF]Simonyan, Karen, and Andrew Zisserman. "Very deep convolutional networks for large-scale imagerecognition." arXiv preprint arXiv:1409.1556 (2014). [PDF]He, Kaiming, et al. "Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition."arXiv preprint arXiv:1406.4729 (2014). [PDF]LeCun, Yann, et al. "Gradient-based learning applied to document recognition." Proceedings of the IEEE86.11 (1998): 2278-2324. [PDF]Fei-Fei, Li, et al. "What do we perceive in a glance of a real-world scene?." Journal of vision 7.1 (2007):10. [PDF]Fei-Fei Li & Andrej Karpathy & Justin JohnsonLecture 1 -474-Jan-16
Lecture 1 - Fei-Fei Li & Andrej Karpathy & Justin Johnson Computer Vision courses @ Stanford CS131 (fall, 2015, Profs. Fei-Fei Li & Juan Carlos . " In Proceedings of the 6th International Joint Conference on Artificial Intelligence (1979): 105-113. [PDF] Fischler, Martin A., and Robert A. Elschlager. "The representation and matching .
Introduction of Chemical Reaction Engineering Introduction about Chemical Engineering 0:31:15 0:31:09. Lecture 14 Lecture 15 Lecture 16 Lecture 17 Lecture 18 Lecture 19 Lecture 20 Lecture 21 Lecture 22 Lecture 23 Lecture 24 Lecture 25 Lecture 26 Lecture 27 Lecture 28 Lecture
SEISMIC: A Self-Exciting Point Process Model for Predicting Tweet Popularity Qingyuan Zhao Stanford University qyzhao@stanford.edu Murat A. Erdogdu Stanford University erdogdu@stanford.edu Hera Y. He Stanford University yhe1@stanford.edu Anand Rajaraman Stanford University anand@cs.stanford.edu Jure Leskovec Stanford University jure@cs.stanford .
Lecture 1: A Beginner's Guide Lecture 2: Introduction to Programming Lecture 3: Introduction to C, structure of C programming Lecture 4: Elements of C Lecture 5: Variables, Statements, Expressions Lecture 6: Input-Output in C Lecture 7: Formatted Input-Output Lecture 8: Operators Lecture 9: Operators continued
ARTIFICIAL INTELLIGENCE LAB STANFORD UNIVERSITY SCHOOL OF ENGINEERING / COMPUTER SCIENCE DEPARTMENT 1 Stanford Artificial Intelligence Lab FEBRUA RY 2 019. 2 STANFORD UNIVERSITY Maneesh Agrawala Professor, Computer Science; Director, the Brown Institute for Media Innovation Computer graphics, human-computer interaction, visualization To improve the effectiveness of media of all kinds Gill .
Domain Adversarial Training for QA Systems Stanford CS224N Default Project Mentor: Gita Krishna Danny Schwartz Brynne Hurst Grace Wang Stanford University Stanford University Stanford University deschwa2@stanford.edu brynnemh@stanford.edu gracenol@stanford.edu Abstract In this project, we exa
Computer Science Stanford University ymaniyar@stanford.edu Madhu Karra Computer Science Stanford University mkarra@stanford.edu Arvind Subramanian Computer Science Stanford University arvindvs@stanford.edu 1 Problem Description Most existing COVID-19 tests use nasal swabs and a polymerase chain reaction to detect the virus in a sample. We aim to
Stanford University Stanford, CA 94305 bowang@stanford.edu Min Liu Department of Statistics Stanford University Stanford, CA 94305 liumin@stanford.edu Abstract Sentiment analysis is an important task in natural language understanding and has a wide range of real-world applications. The typical sentiment analysis focus on
Introduction to Quantum Field Theory for Mathematicians Lecture notes for Math 273, Stanford, Fall 2018 Sourav Chatterjee (Based on a forthcoming textbook by Michel Talagrand) Contents Lecture 1. Introduction 1 Lecture 2. The postulates of quantum mechanics 5 Lecture 3. Position and momentum operators 9 Lecture 4. Time evolution 13 Lecture 5. Many particle states 19 Lecture 6. Bosonic Fock .
