Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.

Deep Learning for Computer Vision: Welcome (UPC TelecomBCN 2016)

1,934 views

Published on

http://imatge-upc.github.io/telecombcn-2016-dlcv/

Deep learning technologies are at the core of the current revolution in artificial intelligence for multimedia data analysis. The convergence of big annotated data and affordable GPU hardware has allowed the training of neural networks for data analysis tasks which had been addressed until now with hand-crafted features. Architectures such as convolutional neural networks, recurrent neural networks and Q-nets for reinforcement learning have shaped a brand new scenario in signal processing. This course will cover the basic principles and applications of deep learning to computer vision problems, such as image classification, object detection or text captioning.

Published in: Technology

Deep Learning for Computer Vision: Welcome (UPC TelecomBCN 2016)

  1. 1. Day 1 Lecture 1 Welcome [course site]
  2. 2. 2 Instructors Xavier Giro-i-Nieto • Web: https://imatge.upc.edu/web/people/xavier-giro Associate Professor at Universitat Politecnica de Catalunya (UPC)
  3. 3. 3 Elisa Sayrol Instructors Associate Professor at Universitat Politècnica de Catalunya (UPC) Web: https://imatge.upc.edu/web/people/elisa-sayrol
  4. 4. 4 Amaia Salvador PhD Candidate Image Processing Group (GPI), Universitat Politècnica de Catalunya https://imatge.upc.edu/web/people/amaia-salvador Escola d’Enginyeria de Terrassa UPC - ESEIAAT Instructors
  5. 5. 5 Jordi Torres 5 • Web: http://www.JordiTorres/Barcelona • Twitter: @JordiTorresBCN Professor at Universitat Politècnica de Catalunya (UPC) Instructors
  6. 6. 6 Eva Mohedano Instructors PhD Candidate Insight Centre for Data Analytics https://www.insight-centre.org/users/eva-mohedano
  7. 7. 7 Kevin McGuinness Research Fellow at Dublin City University (DCU) Insight Centre for Data Analytics https://www.insight-centre.org/users/kevin-mcguinness Instructors
  8. 8. 8 Management Instructor Area Xavier Giró Coordination Kevin McGuinness Lectures Elisa Sayrol Logistics & Evaluation Jordi Torres Lab Amaia Salvador Project Eva Mohedano Web and online material
  9. 9. 9 Teaching assistants / contributors
  10. 10. 10 Acknowledgments
  11. 11. 11 Acknowledgments
  12. 12. 12 Densely linked slides
  13. 13. 13
  14. 14. 14 Motivation Source: 25 Best jobs in America (Glassdoor) The best job in the world: Data scientist.
  15. 15. 15 The Economist, “Million-dollar babies” (02/04/2016) Motivation
  16. 16. 16 Nature, “AI talent grab sparks excitement and concern” (26/04/2016) Motivation
  17. 17. 17 Motivation Exponential increase of generated multimedia content..
  18. 18. 18 Motivation ...keeping a record of the memorable personal moments... Pope Francis @ Philippines, 2015 (Source: AP Photo/Bullit Marquez)
  19. 19. 19 Motivation Pope Francis @ Ecuador, 2015 (Source: AP) ...keeping a record of the memorable personal moments...
  20. 20. 20 Motivation …(or not). Pope Francis @ USA, 2015
  21. 21. 21 Motivation This data growth is motivated by ubiquous mobile access to...
  22. 22. 22 Motivation ...the Internet (for visual data transmission)... Source: Cisco Visual Networking Index (VNI)
  23. 23. 23 Motivation ...and people ! Person of the Year (2006)
  24. 24. 24 Motivation Need computer vision tools to extract knowledge from these large amount of rich visual data.
  25. 25. 25 Course sites https://piazza.com/class#summer2016/230360 http://telecombcn.deeplearning.barcelona
  26. 26. 26 Schedule: Project & Tensorflow BSc Students without project Project Teams 1 & 2 Project Teams 3, 4, 5 3-4 Lectures 4-5 TensorFlow Project 5-6 Lectures 6-7 Project (optional) Project Tensorflow Monday to Thursday Friday BSc Students without project Project Teams 1 & 2 Project Teams 3, 4, 5 3-4 Project expo Teams 3, 4 & 5 4-5 TensorFlow Closing 5-6 Project expo Teams 1 & 2 6-7 Closing Tensorflow
  27. 27. 27 Grading BSc MSc Online Tests 60% 30% Lab 30% 30% Project - 30% Communication - 10% Attendance 10% -10% x miss day
  28. 28. 28 Grading: Online tests [Online test preview]

×