Этот материал находится в платной подписке. Оформи премиум подписку и смотри или слушай Tensorflow 2.0: Deep Learning and Artificial Intelligence, а также все другие курсы, прямо сейчас!
Премиум
  • Урок 1. 00:04:04
    Introduction
  • Урок 2. 00:12:48
    Outline
  • Урок 3. 00:08:27
    Where to get the code
  • Урок 4. 00:12:33
    Intro to Google Colab, how to use a GPU or TPU for free
  • Урок 5. 00:07:55
    Tensorflow 2.0 in Google Colab
  • Урок 6. 00:11:42
    Uploading your own data to Google Colab
  • Урок 7. 00:08:55
    Where can I learn about Numpy, Scipy, Matplotlib, Pandas, and Scikit-Learn?
  • Урок 8. 00:05:52
    How to Succeed in this Course
  • Урок 9. 00:14:27
    What is Machine Learning?
  • Урок 10. 00:16:00
    Code Preparation (Classification Theory)
  • Урок 11. 00:04:39
    Beginner's Code Preamble
  • Урок 12. 00:08:41
    Classification Notebook
  • Урок 13. 00:07:20
    Code Preparation (Regression Theory)
  • Урок 14. 00:10:35
    Regression Notebook
  • Урок 15. 00:09:59
    The Neuron
  • Урок 16. 00:10:55
    How does a model "learn"?
  • Урок 17. 00:06:46
    Making Predictions
  • Урок 18. 00:04:29
    Saving and Loading a Model
  • Урок 19. 00:04:28
    Why Keras?
  • Урок 20. 00:03:04
    Suggestion Box
  • Урок 21. 00:06:01
    Artificial Neural Networks Section Introduction
  • Урок 22. 00:09:41
    Forward Propagation
  • Урок 23. 00:09:44
    The Geometrical Picture
  • Урок 24. 00:17:19
    Activation Functions
  • Урок 25. 00:08:42
    Multiclass Classification
  • Урок 26. 00:12:37
    How to Represent Images
  • Урок 27. 00:12:43
    Code Preparation (ANN)
  • Урок 28. 00:08:37
    ANN for Image Classification
  • Урок 29. 00:11:06
    ANN for Regression
  • Урок 30. 00:16:39
    What is Convolution? (part 1)
  • Урок 31. 00:05:57
    What is Convolution? (part 2)
  • Урок 32. 00:06:42
    What is Convolution? (part 3)
  • Урок 33. 00:15:59
    Convolution on Color Images
  • Урок 34. 00:20:59
    CNN Architecture
  • Урок 35. 00:15:14
    CNN Code Preparation
  • Урок 36. 00:06:47
    CNN for Fashion MNIST
  • Урок 37. 00:04:29
    CNN for CIFAR-10
  • Урок 38. 00:08:52
    Data Augmentation
  • Урок 39. 00:05:15
    Batch Normalization
  • Урок 40. 00:10:23
    Improving CIFAR-10 Results
  • Урок 41. 00:18:28
    Sequence Data
  • Урок 42. 00:10:36
    Forecasting
  • Урок 43. 00:12:02
    Autoregressive Linear Model for Time Series Prediction
  • Урок 44. 00:04:13
    Proof that the Linear Model Works
  • Урок 45. 00:21:35
    Recurrent Neural Networks
  • Урок 46. 00:05:51
    RNN Code Preparation
  • Урок 47. 00:11:12
    RNN for Time Series Prediction
  • Урок 48. 00:08:28
    Paying Attention to Shapes
  • Урок 49. 00:17:36
    GRU and LSTM (pt 1)
  • Урок 50. 00:11:37
    GRU and LSTM (pt 2)
  • Урок 51. 00:09:20
    A More Challenging Sequence
  • Урок 52. 00:19:27
    Demo of the Long Distance Problem
  • Урок 53. 00:04:42
    RNN for Image Classification (Theory)
  • Урок 54. 00:04:01
    RNN for Image Classification (Code)
  • Урок 55. 00:12:04
    Stock Return Predictions using LSTMs (pt 1)
  • Урок 56. 00:05:46
    Stock Return Predictions using LSTMs (pt 2)
  • Урок 57. 00:12:00
    Stock Return Predictions using LSTMs (pt 3)
  • Урок 58. 00:05:15
    Other Ways to Forecast
  • Урок 59. 00:13:13
    Embeddings
  • Урок 60. 00:13:18
    Code Preparation (NLP)
  • Урок 61. 00:05:31
    Text Preprocessing
  • Урок 62. 00:08:20
    Text Classification with LSTMs
  • Урок 63. 00:08:08
    CNNs for Text
  • Урок 64. 00:06:11
    Text Classification with CNNs
  • Урок 65. 00:13:11
    Recommender Systems with Deep Learning Theory
  • Урок 66. 00:09:18
    Recommender Systems with Deep Learning Code
  • Урок 67. 00:08:13
    Transfer Learning Theory
  • Урок 68. 00:05:42
    Some Pre-trained Models (VGG, ResNet, Inception, MobileNet)
  • Урок 69. 00:07:04
    Large Datasets and Data Generators
  • Урок 70. 00:04:52
    2 Approaches to Transfer Learning
  • Урок 71. 00:10:50
    Transfer Learning Code (pt 1)
  • Урок 72. 00:08:13
    Transfer Learning Code (pt 2)
  • Урок 73. 00:15:52
    GAN Theory
  • Урок 74. 00:12:11
    GAN Code
  • Урок 75. 00:06:35
    Deep Reinforcement Learning Section Introduction
  • Урок 76. 00:20:19
    Elements of a Reinforcement Learning Problem
  • Урок 77. 00:09:25
    States, Actions, Rewards, Policies
  • Урок 78. 00:10:08
    Markov Decision Processes (MDPs)
  • Урок 79. 00:04:57
    The Return
  • Урок 80. 00:09:54
    Value Functions and the Bellman Equation
  • Урок 81. 00:07:19
    What does it mean to “learn”?
  • Урок 82. 00:09:50
    Solving the Bellman Equation with Reinforcement Learning (pt 1)
  • Урок 83. 00:12:02
    Solving the Bellman Equation with Reinforcement Learning (pt 2)
  • Урок 84. 00:06:10
    Epsilon-Greedy
  • Урок 85. 00:14:16
    Q-Learning
  • Урок 86. 00:14:06
    Deep Q-Learning / DQN (pt 1)
  • Урок 87. 00:10:26
    Deep Q-Learning / DQN (pt 2)
  • Урок 88. 00:05:58
    How to Learn Reinforcement Learning
  • Урок 89. 00:05:15
    Reinforcement Learning Stock Trader Introduction
  • Урок 90. 00:12:23
    Data and Environment
  • Урок 91. 00:05:41
    Replay Buffer
  • Урок 92. 00:06:57
    Program Design and Layout
  • Урок 93. 00:05:47
    Code pt 1
  • Урок 94. 00:09:41
    Code pt 2
  • Урок 95. 00:06:28
    Code pt 3
  • Урок 96. 00:07:26
    Code pt 4
  • Урок 97. 00:03:37
    Reinforcement Learning Stock Trader Discussion
  • Урок 98. 00:08:20
    Help! Why is the code slower on my machine?
  • Урок 99. 00:05:56
    What is a Web Service? (Tensorflow Serving pt 1)
  • Урок 100. 00:16:57
    Tensorflow Serving pt 2
  • Урок 101. 00:08:31
    Tensorflow Lite (TFLite)
  • Урок 102. 00:08:48
    Why is Google the King of Distributed Computing?
  • Урок 103. 00:07:01
    Training with Distributed Strategies
  • Урок 104. 00:10:03
    Differences Between Tensorflow 1.x and Tensorflow 2.x
  • Урок 105. 00:09:40
    Constants and Basic Computation
  • Урок 106. 00:13:00
    Variables and Gradient Tape
  • Урок 107. 00:10:48
    Build Your Own Custom Model
  • Урок 108. 00:09:12
    Mean Squared Error
  • Урок 109. 00:05:59
    Binary Cross Entropy
  • Урок 110. 00:08:07
    Categorical Cross Entropy
  • Урок 111. 00:07:53
    Gradient Descent
  • Урок 112. 00:04:37
    Stochastic Gradient Descent
  • Урок 113. 00:06:11
    Momentum
  • Урок 114. 00:11:46
    Variable and Adaptive Learning Rates
  • Урок 115. 00:13:16
    Adam (pt 1)
  • Урок 116. 00:11:15
    Adam (pt 2)
  • Урок 117. 00:17:31
    How to install Numpy, Scipy, Matplotlib, Pandas, IPython, Theano, and TensorFlow
  • Урок 118. 00:20:21
    Anaconda Environment Setup
  • Урок 119. 00:22:16
    Installing NVIDIA GPU-Accelerated Deep Learning Libraries on your Home Computer
  • Урок 120. 00:15:55
    How to Code Yourself (part 1)
  • Урок 121. 00:09:24
    How to Code Yourself (part 2)
  • Урок 122. 00:12:30
    Proof that using Jupyter Notebook is the same as not using it
  • Урок 123. 00:10:04
    Is Theano Dead?
  • Урок 124. 00:10:25
    How to Succeed in this Course (Long Version)
  • Урок 125. 00:22:05
    Is this for Beginners or Experts? Academic or Practical? Fast or slow-paced?
  • Урок 126. 00:11:19
    Machine Learning and AI Prerequisite Roadmap (pt 1)
  • Урок 127. 00:16:08
    Machine Learning and AI Prerequisite Roadmap (pt 2)
  • Урок 128. 00:02:49
    What is the Appendix?
  • Урок 129. 00:05:32
    BONUS: Where to get discount coupons and FREE deep learning material