Download as PDF, PPTX
Uploaded byHopeBay Technologies, Inc.
Deep Learning in a nutshell
The document provides an introduction to deep learning, focusing on its definition, applications in classification problems, and the use of TensorFlow for model training. It covers the structure of deep neural networks, the training process, and offers resources for practical implementation. Additionally, it discusses deep learning's suitability for various tasks, including handwriting recognition and its deployment in products by Google.
More Related Content
![[2A4]DeepLearningAtNAVER](https://cdn.slidesharecdn.com/ss_thumbnails/2a4deeplearningatnaver-140929210707-phpapp01-thumbnail.jpg?width=640&height=640&fit=bounds)
Similar to Deep Learning in a nutshell
Deep Learning in a nutshell
- 1. Deep Learning in anutshell JohnsonChen @ HB TechFriday
- 2. Agenda 1. Introduction toDeep Learning 2. Training You Own Deep Learning Model a. Introduction to Tensorflow
- 3. What’s deep learning 1.Deep learning is part of a broader family of machine learning methods based on learning representations of data. 2. Deep learning can be applied to binary classification problem ( ), multiclass classification problem ( ). 3. Can we make machine learn by itself? https://en.wikipedia.org/wiki/Deep_learning#Definitions
- 4.
- 5. Let’s talk aboutclassification http://www.louisdorard.com/blog/when-machine-learning-fails
- 6. Let’s talk aboutclassification ( X1, X2, … ) Model
- 7. Build our ownmodel ( X1, X2 ) (1, 1) + (1, 0) + (0, 1) + (0, 0) -
- 8. (1, 1) (1, 0) (0,1) (0, 0) This is our model
- 10. (1, 1) (1, 0) (0,1) (0, 0) (0.3, 0.3)
- 11. What if ... (1,1) - (1, 0) + (0, 1) + (0, 0) -
- 12. (1, 1) (1, 0) (0,1) (0, 0)
- 13. To make it“non-linear”
- 15. Activation Function (relu: rectifiedlinear unit)
- 16.
- 17. So what isdeep learning?
- 18. Artificial Neural Network(ANN) http://cs231n.github.io/neural-networks-1/
- 19.
- 20. Deep Learning (DeepNeural Network, DNN) Deep = many hidden layers 6 ~ 8 hidden layers http://markus.com/deep-learning-101/
- 21.
- 22.
- 23.
- 24. How to trainmodel?
- 25. (0, 1) (0, 0) (1,1) (1, 0)
- 26. Let’s try handwritingrecognition Most of slides are borrowed from Hung-yi Lee deep learning talk.
- 27.
- 29. 784 28 * 28= 784
- 30.
- 35. Agenda 1. Introduction toDeep Learning 2. Training you own Deep Learning model a. use Tensorflow Most of slides are borrowed from Dr. Chung-Cheng Chiu deep learning talk
- 38. TensorFlow Developed by GoogleBrain Team Initial release: November 9, 2015 Used for both Google production and research. Production: 50 different teams in dozens of commercial Google products, such as Google Voice, Gmail, Google Photos, and Search, etc Feature: Python, C/C++ API support multiple CPUs and GPUs support mobile computing platforms, including Android and Apple's iOS
- 39. TensorFlow = Tensor+ Flow Tensor: n-dimensional arrays Flow: A sequence of tensor operations Deep Learning is suitable for TensorFlow, but TensorFlow can do more
- 40.
- 41. They are alltensor
- 42. Implement it 784 300100 10 w1 w2 w3 b1 b2 b3 28 * 28 = 784 0 0 0 0 0 1 0 0 0 0
- 43.
- 44. Implement it 1. Definevariables 2. Create (deep) neural network 3. Define cost function, optimizer 4. Train model parameter
- 45.
- 46. Define variables 784 300100 10 x y w1 w2 w3 b1 b2 b3
- 47. Create (deep) neuralnetwork 784 300 100 10 x y w1 w2 w3 b1 b2 b3
- 48. Define cost function,optimizer
- 49.
- 51. Save your model #defaults to saving all variables - in this case w and b saver = tf.train.Saver()
- 52.
- 53.
- 55.
- 56.
- 57. AlphaGo: Deep Learningvs AlphaGo Google DeepMind 3 9 3 15 AlphaGo 5 12 1. 3 9 ( ) 2. 3 10 ( ) 3. 3 12 ( ) 4. 3 13 ( ) 5. 3 15 ( ) Read: Google
- 58. Conclusion Neural network, Deeplearning Create a framework to let machine learn by itself Sometimes it is too complex to debug TensorFlow tool Try to train you own model. Define input, out, and run/train it
- 59.
- 60.