Deep machine learning by Mario Cho
•
2 likes•1,277 views
This document introduces machine learning and artificial intelligence concepts. It discusses neural networks, deep learning, and TensorFlow. It provides examples of using neural networks for tasks like image recognition, language processing, and generating images. Deep learning is taking off due to large neural networks and labeled training data. TensorFlow is an open source software for machine learning tasks.
Recommended
Recommended
More Related Content
What's hot
What's hot (20)
Viewers also liked
Similar to Deep machine learning by Mario Cho
Similar to Deep machine learning by Mario Cho (20)
More from Mario Cho
More from Mario Cho (9)
Recently uploaded
Recently uploaded (20)
Deep machine learning by Mario Cho
- 1. 제로부터 시작하는 인공지능 Artificial Intelligence 중앙대학교 의료보안연구소 Mario Cho (조만석) hephaex@gmail.com
- 2. Contents • 기계학습이란? • 신경망이란 • 인공지능 SW TensorFlow • 딥러닝 실습 • 딥러닝 응용
- 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 Chungan Univercity Mario Cho hephaex@gmail.com
- 4. 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. Google (2)
- 7. 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.
- 8. What is Artificial Intelligence?
- 9. Artificial Intelligence Understand information, To Learn, To Reason, & Act upon it
- 11. Make predictions on data
- 12. 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
- 13. 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
- 14. What is a neural network? Yes/No (Mug or not?) Data (image) ! x1 ∈!5 ,!x2 ∈!5 x2 =(W1 ×x1 )+ x3 =(W2 ×x2 )+ x1 x2 x3 x4 x5 W4W3W2W1
- 15. Neural network vs Learning network Neural Network Deep Learning Network
- 17. 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
- 19. Why is Deep Learning taking off? Engine Fuel Large neural networks Labeled data (x,y pairs)
- 20. Training Process
- 21. Deep learning - CNN
- 22. Deep learning : CNN
- 23. The Big Players
- 24. Open Source Software for Machine Learning Caffe Theano Convnet.js Torch7 Chainer DL4J TensorFlow Neon SANOA Summingbird Apache SA Flink ML Mahout Spark MLlib RapidMiner Weka Knife Scikit-learn Amazon ML BigML DataRobot FICO Google prediction API HPE haven OnDemand IBM Watson PurePredictive Yottamine Deep Learning Stream Analytics Big Data Machine Learning Data Mining Machine Learning As a Service Pylearn2
- 26. * Source: Oriol Vinyals – Research Scientist at Google Brain
- 27. Expressing High-Level ML Computations • Core in C++ • Different front ends for specifying/driving the computation • Python and C++ today, easy to add more * Source: Jeff Dean– Research Scientist at Google Brain
- 28. Hello World on TensorFlow
- 29. Image recognition in Google Map * Source: Oriol Vinyals – Research Scientist at Google Brain
- 30. Deep Learning Hello World == MNIST
- 31. MNIST (predict number of image)
- 32. CNN (convolution neural network) training
- 33. MNIST code
- 34. MNIST
- 37. Face recognition data- sets?
- 38. 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
- 39. Image Recognition * Source: Oriol Vinyals – Research Scientist at Google Brain
- 40. Object Classification and Detection
- 41. How to the Object recognition ?
- 42. Language Generating * Source: Oriol Vinyals – Research Scientist at Google Brain
- 45. Neuro Painter
- 46. Deep Art
- 47. Inceptionism
- 48. Automatic Colorization of Black and White Images
- 49. Image Generate
- 51. Scene Parsing [Farabet et al. ICML 2012, PAMI 2013]
- 52. Scene Parsing [Farabet et al. ICML 2012, PAMI 2013]
- 53. Auto pilot car
- 54. Q-Learning
- 56. How do data science techniques scale with amount of data?
- 58. GPU
- 60. Thanks you! Q&A