Ce diaporama a bien été signalé.
Nous utilisons votre profil LinkedIn et vos données d’activité pour vous proposer des publicités personnalisées et pertinentes. Vous pouvez changer vos préférences de publicités à tout moment.

Deep Learning - Convolutional Neural Networks

62 277 vues

Publié le

Presentation about Deep Learning and Convolutional Neural Networks.

Publié dans : Technologie
  • Soyez le premier à commenter

Deep Learning - Convolutional Neural Networks

  1. 1. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A Deep Learning Convolutional Neural Networks Christian S. Perone christian.perone@gmail.com
  2. 2. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A WHO AM I Christian S. Perone Software Designer Blog http://blog.christianperone.com Open-source projects https://github.com/perone Twitter @tarantulae
  3. 3. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A AGENDA DEEP LEARNING Introduction Traditional vs Deep learning ImageNet Challenge Deep learning in art NEURAL NETWORKS Neural network basics Making it possible CONVOLUTIONAL NEURAL NETWORKS Architecture overview Convolutional layer Pooling layer Dense layers and classification Deep CNNs Important ideas Transfer learning INTERESTING CASES Recommendation Natural language processing Image/video processing Q&A
  4. 4. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A Section I DEEP LEARNING
  5. 5. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A WHAT IS DEEP LEARNING ? Multiple definitions, however, these definitions have in common: Multiple layers of processing units; Supervised or unsupervised learning of feature representations in each layer, with the layers forming a hierarchy from low-level to high-level features.
  6. 6. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A COMPOSITIONAL DATA NATURAL DATA IS COMPOSITIONAL.
  7. 7. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A COMPOSITIONAL DATA Image Source: Convolutional Deep Belief Networks. Honglak Lee, et. al.
  8. 8. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A COMPOSITIONAL DATA Sound Source: Large Scale Deep Learning. Jeff Dean, joint work with Google.
  9. 9. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A ONE SLIDE INTRO TO MACHINE LEARNING Source: Scikit-Learn (scikit-learn.org)
  10. 10. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A TRADITIONAL VS DEEP LEARNING For many years, we developed feature extractors. Source: Deep Learning Methods for Vision (Honglak Lee)
  11. 11. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A TRADITIONAL VS DEEP LEARNING Feature extractors, required: Expert knowledge Time-consuming hand-tuning In industrial applications, this is 90% of the time Sometimes are problem specific
  12. 12. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A TRADITIONAL VS DEEP LEARNING Feature extractors, required: Expert knowledge Time-consuming hand-tuning In industrial applications, this is 90% of the time Sometimes are problem specific But, what if we could learn feature extractors ?
  13. 13. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A TRADITIONAL VS DEEP LEARNING TRADITIONAL APPROACH The traditional approach uses fixed feature extractors.
  14. 14. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A TRADITIONAL VS DEEP LEARNING TRADITIONAL APPROACH The traditional approach uses fixed feature extractors. DEEP LEARNING APPROACH Deep Learning approach uses trainable feature extractors.
  15. 15. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A TRADITIONAL VS DEEP LEARNING Source: Lee et.al., ICML2009
  16. 16. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A IMAGENET Source: t-SNE visualization of CNN codes. Andrej Karpathy ≈ 20.000 object classes ≈ 14 million images
  17. 17. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A IMAGENET Source: ImageNet
  18. 18. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A IMAGE CLASSIFICATION Source: We’ve Been Dressing Animals Up as People Way Before the Internet. Jes Greene. Image classification, can get really hard.
  19. 19. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A IMAGENET CHALLENGE Source: Musings on Deep Learning. Li Jiang.
  20. 20. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A DEEP DREAMS Source: Google Inceptionism
  21. 21. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A ART STYLE Source: A Neural Algorithm of Artistic Style. Leon A. Gatys et. al.
  22. 22. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A ART STYLE Source: A Neural Algorithm of Artistic Style. Leon A. Gatys et. al.
  23. 23. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A ART STYLE Source: A Neural Algorithm of Artistic Style. Leon A. Gatys et. al.
  24. 24. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A ART STYLE Source: A Neural Algorithm of Artistic Style. Leon A. Gatys et. al.
  25. 25. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A Section II NEURAL NETWORKS
  26. 26. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A NEURAL NETWORK ARCHITECTURE Source: Neural Networks and Deep Learning. Michael Nielsen. Source: Practical Deep N. Networks. Yuhuang Hu et. al.
  27. 27. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A MNIST DIGITS CLASSIFICATION Segmented digits MNIST digit format (28 x 28 = 784 pixels) Source: Neural Networks and Deep Learning. Michael Nielsen.
  28. 28. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A NEURAL NETWORK ARCHITECTURE Source: Neural Networks and Deep Learning. Michael Nielsen. 2.225 of 10.000 test images (22.25 % accuracy)
  29. 29. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A NEURAL NETWORK ARCHITECTURE Source: Neural Networks and Deep Learning. Michael Nielsen. 2.225 of 10.000 test images (22.25 % accuracy) An SVM classifier can get 9.435 of 10.000 ( % 94.35)
  30. 30. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A NEURAL NETWORK ARCHITECTURE Source: Neural Networks and Deep Learning. Michael Nielsen. 2.225 of 10.000 test images (22.25 % accuracy) An SVM classifier can get 9.435 of 10.000 ( % 94.35) SVM with hyperparameter optimization can get 98.5%
  31. 31. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A NEURAL NETWORK ARCHITECTURE Can we do better ?
  32. 32. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A NEURAL NETWORK ARCHITECTURE Can we do better ? In fact, yes. The current record is from 2013 and it classifies 9.979 of 10.000 images correctly. The performance is human-equivalent (or better).
  33. 33. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A NEURAL NETWORK ARCHITECTURE Can we do better ? In fact, yes. The current record is from 2013 and it classifies 9.979 of 10.000 images correctly. The performance is human-equivalent (or better). Source: Neural Networks and Deep Learning. Michael Nielsen. Neural networks can accurately classify all but 21 of the 10,000 test images.
  34. 34. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A WHAT CHANGED ? For approximately 20 years, attempts were made to train deeper neural networks (with more than one hidden layer), however rarely with benefits (vanishing gradient).
  35. 35. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A WHAT CHANGED ? In 2006, a major breakthrough was made in deep architectures, following three key principles: Unsupervised learning of representations is used to pre-train each layer
  36. 36. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A WHAT CHANGED ? In 2006, a major breakthrough was made in deep architectures, following three key principles: Unsupervised learning of representations is used to pre-train each layer Unsupervised training of one layer at a time, on top of the previously trained ones. The representation learned at each level is the input for the next layer.
  37. 37. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A WHAT CHANGED ? In 2006, a major breakthrough was made in deep architectures, following three key principles: Unsupervised learning of representations is used to pre-train each layer Unsupervised training of one layer at a time, on top of the previously trained ones. The representation learned at each level is the input for the next layer. Use supervised training to fine-tune all the layers (in addition to one or more additional layers that are dedicated to producing predictions).
  38. 38. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A WHAT CHANGED ? After the 2006 breakthrough, a lot of ideas were also developed. Nowadays, pre-training is almost obsolete.
  39. 39. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A WHAT CHANGED ? After the 2006 breakthrough, a lot of ideas were also developed. Nowadays, pre-training is almost obsolete. New activation functions
  40. 40. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A WHAT CHANGED ? After the 2006 breakthrough, a lot of ideas were also developed. Nowadays, pre-training is almost obsolete. New activation functions Regularization methods
  41. 41. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A WHAT CHANGED ? After the 2006 breakthrough, a lot of ideas were also developed. Nowadays, pre-training is almost obsolete. New activation functions Regularization methods Initialization methods
  42. 42. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A WHAT CHANGED ? After the 2006 breakthrough, a lot of ideas were also developed. Nowadays, pre-training is almost obsolete. New activation functions Regularization methods Initialization methods Data augmentation
  43. 43. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A WHAT CHANGED ? After the 2006 breakthrough, a lot of ideas were also developed. Nowadays, pre-training is almost obsolete. New activation functions Regularization methods Initialization methods Data augmentation Optimization techniques
  44. 44. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A WHAT CHANGED ? Another reason on why Deep Learning is possible, is the availability of lots of data (i.e. ImageNet).
  45. 45. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A WHAT CHANGED ? Another reason on why Deep Learning is possible, is the availability of lots of data (i.e. ImageNet). GPGPU also plays an important role on this. For instance, an NVIDIA GPU (1 Tesla K40 GPU) training a 7 layer Convolutional Neural Network is nearly 9x faster than CPU. Convolutions — 80-90% of execution time Pooling Activations
  46. 46. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A WHAT CHANGED ? Companies are working on solutions for Deep Learning acceleration:
  47. 47. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A WHAT CHANGED ? Companies are working on solutions for Deep Learning acceleration: NVIDIA NVIDIA created a entire plaftorm stack dedicated to work with Deep Learning, called DIGITS. Their GPUs are widely used in Deep Learning.
  48. 48. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A WHAT CHANGED ? Companies are working on solutions for Deep Learning acceleration: NVIDIA NVIDIA created a entire plaftorm stack dedicated to work with Deep Learning, called DIGITS. Their GPUs are widely used in Deep Learning. AMAZON Amazon AWS also create EC2 instances with NVIDIA GPUs (with 4GB of memory and 1536 CUDA cores). Lots of AMIs with Deep Learning software ecosystem already installed.
  49. 49. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A WHAT CHANGED ? Companies are working on solutions for Deep Learning acceleration: NVIDIA NVIDIA created a entire plaftorm stack dedicated to work with Deep Learning, called DIGITS. Their GPUs are widely used in Deep Learning. AMAZON Amazon AWS also create EC2 instances with NVIDIA GPUs (with 4GB of memory and 1536 CUDA cores). Lots of AMIs with Deep Learning software ecosystem already installed. MICROSOFT Microsoft announced that it will offer NVIDIA GPUs on its Azure cloud platform.
  50. 50. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A Section III CONVOLUTIONAL NEURAL NETWORKS
  51. 51. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A CONVOLUTIONAL NEURAL NETWORKS Convolutional Neural Networks (or convnets) are based on the following principles: Local receptive fields Shared weights Pooling (or down-sampling) This special neural network architecture takes advantage of the spatial structure of data.
  52. 52. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A CONVOLUTIONAL NEURAL NETWORKS Convolutional Neural Networks (or convnets) are based on the following principles: Local receptive fields Shared weights Pooling (or down-sampling) This special neural network architecture takes advantage of the spatial structure of data. Source: Deeply-Supervised Nets. Zhuowen Tu.
  53. 53. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A LOCAL CONNECTIVITY Let’s take the MNIST digits images as input of our convnet. These images are 28x28 pixels: 28x28 image Local connectivity (5x5) Source: Neural Networks and Deep Learning. Michael Nielsen.
  54. 54. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A LOCAL CONNECTIVITY
  55. 55. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A LOCAL CONNECTIVITY By “sliding” it, we create a feature map of or 24x24 neurons in the hidden layer. We can also have a different stride and padding.
  56. 56. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A SHARED WEIGHTS In this local receptive field, Convolutional Neural Networks use the same shared weights for each of the 24x24 hidden neurons. This means that we have a great advantage of parameter reduction, for instance, for a 5x5 receptive field, we’ll need only 25 shared weights1. 1 Excluding the bias
  57. 57. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A SHARED WEIGHTS In this local receptive field, Convolutional Neural Networks use the same shared weights for each of the 24x24 hidden neurons. This means that we have a great advantage of parameter reduction, for instance, for a 5x5 receptive field, we’ll need only 25 shared weights1. 20 feature maps using 5x5 — 20*26 = 520 weights A fully connected first layer, with 784=28*28 input neurons, and a relatively modest 30 hidden neurons, would produce 784*30 = 23.520 weights, more than 40 times as many parameters as the convolutional layer. 1 Excluding the bias
  58. 58. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A CONVOLUTIONAL LAYER The shared weights and bias are called kernel or filter. Convolutional layers provides translation invariance. Since these filters works on every part of the image, they are “searching” for the same feature everywhere in the image.
  59. 59. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A ARCHITECTURE OVERVIEW Input layer – 28x28 pixels Convolutional layer — 3 feature maps (5x5 kernel)
  60. 60. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A POOLING LAYER Pooling layers are usually present after a convolutional layer. They provide a down-sampling of the convolution output. In the example above, a 2x2 region is being used as input of the pooling.
  61. 61. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A POOLING LAYER There are different types of pooling, the most used is the max-pooling and average pooling: Pooling layers downsamples the volume spatially, reducing small translations of the features. They also provide a parameter reduction. Source: CS231n Convolutional Neural Networks for Visual Recognition.
  62. 62. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A POOLING LAYER Max-pooling is how the network asks whether a feature is found anywhere in some region of the image. After that, it will lose the exact position.
  63. 63. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A ARCHITECTURE OVERVIEW Input layer – 28x28 pixels Convolutional layer — 3 feature maps (5x5 kernel) Pooling Layer — 2x2, resulting in 3x12x12
  64. 64. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A CLASSIFICATION As you can see, we then add a dense fully-connected layer (usually using softmax) at the end of the neural network in order to get predictions for the problem we’re working on (10 classes, 10 digits).
  65. 65. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A GOING DEEPER We have defined all the components required to create a Convolutional Neural Network, but you’ll rarely see a shallow convnet like that.
  66. 66. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A GOING DEEPER Actually, experiments demonstrated that the replication of convolutional + pooling layers produces better results the deeper you go. Winners of ImageNet challenge, have more than 15 layers (VGGNet has 19 layers).
  67. 67. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A GOING DEEPER Source: Rotation-invariant convolutional neural networks for galaxy morphology prediction. Sander Dieleman et. al. Galaxy Zoo best performing network (winner of the challenge).
  68. 68. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A DROPOUT TECHNIQUE Source: “Dropout: A Simple Way to Prevent Neural Networks from Overfitting”. Nitish Srivastava et. al. The dropout technique helps with the overfitting, specially on dense layers. Drop occur only at training time, not on test time.
  69. 69. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A ACTIVATION FUNCTIONS Source: Big Data Analytics. Fei Wang. ReLu helps with the vanishing gradient problem ReLu generates sparsity
  70. 70. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A DATA AUGMENTATION Data augmentation can help with overfitting and will certainly improve improve results. Source: Rotation-invariant convolutional neural networks for galaxy morphology prediction. Sander Dieleman et. al.
  71. 71. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A DATA AUGMENTATION Data augmentation can help with overfitting and will certainly improve improve results. Source: Rotation-invariant convolutional neural networks for galaxy morphology prediction. Sander Dieleman et. al. Small rotations Small translation Scaling Flipping Brightness Noise
  72. 72. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A TRANSFER LEARNING Features learned by Convolutional Neural Networks on large dataset problem (i.e. ImageNet), can be helpful on different problems. It’s very common to pre-train a convnet on ImageNet and then use it as a fixed feature extractor or as initialization. CONVNETS AS FEATURE EXTRACTORS We can remove the last layer and then use these features to extract features, these features are very useful features for classification. Some people use these features with LSH (locality-sensitive hashing) to scale large databases for image search. You can also use these features as input for a SVM classifier for instance.
  73. 73. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A TRANSFER LEARNING Features learned by Convolutional Neural Networks on large dataset problem (i.e. ImageNet), can be helpful on different problems. It’s very common to pre-train a convnet on ImageNet and then use it as a fixed feature extractor or as initialization. FINE-TUNING THE CONVNETS You can use a pre-trained convnet to continue its training on your data and thus fine-tune the weights for your problem. First layers of a convnet contains generic features (i.e. edge detectors, etc.) that should be helpful in many tasks. Deeper layers becomes progressively specific to the details of the classes of the original problem.
  74. 74. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A Section IV INTERESTING CASES
  75. 75. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A MUSIC RECOMMENDATION Source: Recommending music on Spotify with deep learning. Sander Dieleman. This is an example architecture from Spotify, using Convolutional Neural Network for music recommendation.
  76. 76. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A MUSIC RECOMMENDATION Learned filters at first convolutional layer. The time axis is horizontal, the frequency axis is vertical (frequency increases from top to bottom)
  77. 77. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A NATURAL LANGUAGE PROCESSING Source: Text understanding from scratch. Xiang Zhang, Yann LeCun. Deciding if a review posted on Amazon is positive or negative with 96% accuracy, and predict the actual number of stars with 73% accuracy.
  78. 78. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A WORD2VEC Source: Distributed Representations of Sentences and Documents. Quoc Le, Tomas Mikolov. Word vectors (trained with up to hundreds of billions of words).
  79. 79. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A WORD2VEC Source: Distributed Representations of Sentences and Documents. Quoc Le, Tomas Mikolov. Word vectors (trained with up to hundreds of billions of words). With nice properties: v(’Paris’) - v(’France’) + v(’Italy’ ) ≈ v(’Rome’) v(’king’) - v(’man’) + v(’woman’) ≈ v(’queen’) No deep learning and no convnet, but a great distributed representation example.
  80. 80. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A WORD2VEC Machine Translation Source: DL4J.
  81. 81. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A DOC2VEC Sentiment analysis Source: Distributed Representations of Sentences and Documents. Quoc Le, Tomas Mikolov.
  82. 82. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A INTERESTING FRAMES Google recently put in production a Deep Neural Network to improve YouTube video thumbnails. Source: Google Research.
  83. 83. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A SPATIAL TRANSFORMER NETWOKRS Spatial Transformer Networks can learn transformations. Source: Spatial Transformer Networks. Max Jaderberg, et. al.
  84. 84. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A DEEPFACE BY FACEBOOK Source: DeepFace: Closing the Gap to Human-Level Performance in Face Verification. Yaniv Taigman, et. al.
  85. 85. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A Section V Q&A
  86. 86. DEEP LEARNING NEURAL NETWORKS CONVOLUTIONAL NEURAL NETWORKS INTERESTING CASES Q&A Q&A

×