Introduce Deep learning & A.I. Applications
10 likes4,006 views
This document provides an overview of deep machine learning and its applications. It introduces Mario Cho and his experience with image recognition, medical data processing, and open source software development. The document then discusses neural networks, deep learning techniques, and how deep learning can be applied to areas like image recognition, natural language processing, and autonomous vehicles. Examples of deep learning applications include image captioning, machine translation, and generating synthetic images from sketches.
![Scene Parsing
[Farabet et al. ICML 2012, PAMI 2013]](https://image.slidesharecdn.com/koss6b23deepmachinelearningmariochor10-161216033723/85/Introduce-Deep-learning-A-I-Applications-39-320.jpg)
![Scene Parsing
[Farabet et al. ICML 2012, PAMI 2013]](https://image.slidesharecdn.com/koss6b23deepmachinelearningmariochor10-161216033723/85/Introduce-Deep-learning-A-I-Applications-40-320.jpg)
Introduce Deep learning & A.I. Applications
- 1. 인공지능(딥러닝) 이해와 응용 Deep Machine Learning & Applications KOSS Lab. 2기 Mario Cho (조만석) hephaex@gmail.com
- 2. Contents • 기계학습 (NNs) • Neural Networks • 딥러닝 기술 • 활용방안
- 3. Mario Cho Development Experience ◆ Image Recognition using Neural Network ◆ Bio-Medical Data Processing ◆ Human Brain Mapping on High Performance Computing ◆ Medical Image Reconstruction (Computer Tomography) ◆ Enterprise System ◆ Open Source Software Developer Open Source Software Developer ◆ OPNFV (NFV&SDN) & OpenStack ◆ Machine Learning (TensorFlow) Book ◆ Unix V6 Kernel Korea Open Source Software Lab. Mario Cho hephaex@gmail.com
- 5. The Future of Jobs “The Fourth Industrial Revolution, which includes developments in previously disjointed fields such as artificial intelligence & machine-learning, robotics, nanotechnology, 3-D printing, and genetics & biotechnology, will cause widespread disruption not only to business models but also to labor market over the next five years, with enormous change predicted in the skill sets needed to thrive in the new landscape.”
- 6. What is the Machine Learning ? • Field of Computer Science that evolved from the study of pattern recognition and computational learning theory into Artificial Intelligence. • Its goal is to give computers the ability to learn without being explicitly programmed. • For this purpose, Machine Learning uses mathematical / statistical techniques to construct models from a set of observed data rather than have specific set of instructions entered by the user that define the model for that set of data.
- 7. Required of New type of Computing understand information, to learn, to reason, and act upon it
- 8. Traditional learning vs Deep Machine Learning Eiffel Tower Eiffel Tower RAW data RAW data Deep Learning Network Feature Extraction Vectored Classification Traditional Learning Deep Learning
- 9. Neuron
- 11. Brain Map
- 12. hippocampus
- 13. Neural network vs Learning network Neural Network Deep Learning Network
- 15. Neural Network 2.7 -8.6 0.002 f(x) 1.4 -2.5 -0.06 x = -0.06×2.7 + 2.5×8.6 + 1.4×0.002 = 21.34
- 16. Neural Network : x1 XNOR x2 +1 x1 x2 +1 a1(2) a2(2) a1(3) -30 20 20 10 -20 -10 -10 10 -20 x1 x2 a1(2) a2(2) a1(3) 0 0 0 1 1 0 1 0 0 0 1 0 0 0 0 1 1 1 0 0 Output 10
- 17. Multi-layer Neural Networks Train this layer first
- 18. Multi-layer Neural Networks Train this layer first then this layer then this layer then this layer finally this layer
- 19. Tic Tac Toc
- 20. AlphaGo RAW data Layer1 Policy network & value network Selection Expansions Evaluation Backup ~ Layer13
- 21. Deep learning - CNN
- 22. Image recognition in Google Map * Source: Oriol Vinyals – Research Scientistat Google Brain
- 23. Deep Learning Hello World == MNIST
- 24. MNIST (predict number of image)
- 25. CNN (convolution neural network) training
- 26. MNIST
- 28. Human-Level Object Recognition • ImageNet • Large-Scale Visual Recognition Challenge –Image Classification / Localization –1.2M labeled images, 1000 classes –Convolutional Neural Networks (CNNs) has been dominating the contest since.. – 2012 non-CNN: 26.2% (top-5 error) – 2012: (Hinton, AlexNet)15.3% – 2013: (Clarifai) 11.2% – 2014: (Google, GoogLeNet) 6.7% – 2015: (Google) 4.9% – Beyond human-level performance
- 29. Hierarchical Representation of Deep Learning * Source: : Honglak Lee and colleagues (2011) as published in “Unsupervised Learning of Hierarchical Representations with Convolutional Deep Belief Networks”.
- 30. * Source: : Honglak Lee and colleagues (2011) as published in “Unsupervised Learning of Hierarchical Representations with Convolutional Deep Belief Networks”. Deep Learning (object parts)
- 32. Face recognition data- sets?
- 33. Human-Level Face Recognition • Convolutional neural networks based face recognition system is dominant • 99.15% face verification accuracy on LFW dataset in DeepID2 (2014) – Beyond human-level recognition Source: Taigman et al. DeepFace: Closing the Gap to Human-Level Performance in Face Verification, CVPR’14
- 34. Image Recognition * Source: Oriol Vinyals – Research Scientistat Google Brain
- 35. Object Classification and Detection
- 36. How to the Object recognition ?
- 38. Language Generating * Source: Oriol Vinyals – Research Scientistat Google Brain
- 39. Scene Parsing [Farabet et al. ICML 2012, PAMI 2013]
- 40. Scene Parsing [Farabet et al. ICML 2012, PAMI 2013]
- 41. Auto pilot car
- 42. Automatic Colorization of Black and White Images
- 43. Generate sounds on old-movies
- 44. Automatic Machine Translation • Automatic Translation of Text. • Automatic Translation of Images.
- 46. Text Generation
- 47. create stylized images from rough sketches.
- 49. Thanks you! Q&A