Deep Learning by Andrew Ng [Full Course]
5.0
(0)
6 learners
What you'll learn
This course includes
- 13.5 hours of video
- Certificate of completion
- Access on mobile and TV
Course content
1 modules • 98 lessons • 13.5 hours of video
Deep Learning by Andrew Ng [Full Course]
98 lessons
• 13.5 hours
Deep Learning by Andrew Ng [Full Course]
98 lessons
• 13.5 hours
- 1. What is Deep Learning?05:32
- 2. What is a Neural Network?07:17
- 3. Supervised Learning with Neural Networks08:29
- 4. Drivers Behind the Rise of Deep Learning10:22
- 5. Binary Classification in Deep Learning08:24
- 6. Logistic Regression06:00
- 7. Logistic Regression Cost Function08:12
- 8. Gradient Descent11:24
- 9. Derivatives07:11
- 10. Derivatives Examples10:28
- 11. Computation Graph03:34
- 12. Derivatives with a Computation Graph14:34
- 13. Logistic Regression Derivatives06:43
- 14. Gradient Descent on m Training Examples08:01
- 15. Vectorization08:05
- 16. More Vectorization Examples06:20
- 17. Vectorizing Logistic Regression07:33
- 18. Vectorizing Logistic Regression's Gradient Computation09:38
- 19. Broadcasting in Python11:06
- 20. Python-Numpy06:50
- 21. Jupyter-iPython03:44
- 22. Logistic Regression Cost Function Explanation07:15
- 23. Neural Network Overview04:27
- 24. Neural Network Representation05:15
- 25. Computing a Neural Network's Output09:58
- 26. Vectorizing Across Multiple Training Examples09:06
- 27. Vectorized Implementation Explanation07:38
- 28. Activation Functions10:57
- 29. Why Non-Linear Activation Function?05:36
- 30. Derivatives of Activation Functions07:58
- 31. Gradient Descent for Neural Networks09:58
- 32. BackPropagation Intuition (Optional)15:49
- 33. Random Initialization of Weights07:58
- 34. Deep L-layer Neural Network05:52
- 35. Forward Propagation in Deep Networks07:16
- 36. Getting your Matrix Dimension Right11:10
- 37. Why DEEP representation?10:34
- 38. Building Blocks of Deep Neural Network08:34
- 39. Forward Propagation for Layer L10:30
- 40. Parameters vs Hyperparameters07:17
- 41. Brain and Deep Learning03:18
- 42. Train/Dev/Test sets12:05
- 43. Bias/ Variance08:47
- 44. Basic "Recipe" of Machine Learning06:22
- 45. Regularization09:43
- 46. Why Regularization reduces Overfitting?07:10
- 47. Dropout Regularization09:26
- 48. Why does drop-out work?07:05
- 49. Other Regularization Methods08:24
- 50. Normalizing Input05:31
- 51. Vanishing / Exploding Gradients06:08
- 52. Weight Initialization for deep networks06:12
- 53. Numerical Approximation of Gradients06:36
- 54. Gradient Checking06:35
- 55. Gradient Checking Implantation Notes05:19
- 56. Mini Batch Gradient Descent11:29
- 57. Understanding Mini-Batch Gradient Descent11:19
- 58. Exponentially Weighted Averages05:59
- 59. Understanding Exponentially Weighted Averages09:42
- 60. Bias Correction in Exponentially Weighted Average04:12
- 61. Gradient Descent with Momentum09:21
- 62. RMSprop07:42
- 63. Adam Optimization Algorithm07:08
- 64. Learning Rate Decay06:45
- 65. The Problem of Local Optima05:24
- 66. Tunning Process07:11
- 67. Right Scale for Hyperparameters08:51
- 68. Hyperparameters tuning in Practice: Panda vs. Caviar06:52
- 69. Batch Norm08:55
- 70. Fitting Batch Norm into a Neural Network12:56
- 71. Why Does Batch Nom Work?11:40
- 72. Batch Norm at Test Time05:47
- 73. Softmax Regression11:48
- 74. Training a Softmax Classifier10:08
- 75. Deep Learning Frameworks04:16
- 76. TensorFlow16:08
- 77. Why ML Strategy?02:43
- 78. Orthogonalization10:39
- 79. Single Number Evaluation Metric07:17
- 80. Satisfying and Optimizing Metrics05:59
- 81. train/dev/test distributions06:36
- 82. Size of dev and test sets05:40
- 83. When to change dev/test sets and metrics?11:08
- 84. Why human-level performance?05:47
- 85. Avoidable Bias07:00
- 86. Understanding Human-Level Performance11:12
- 87. Surpassing Human-Level Performance06:22
- 88. Improving Your Model Performance06:21
- 89. Carrying Out Error Analysis10:32
- 90. Cleaning Up Incorrect Labeled Data13:06
- 91. Build Your First System Quickly, Then Iterate06:02
- 92. Training and Testing on Different Distributions10:56
- 93. Bias and Variance with Mismatched data distributions18:17
- 94. Addressing Data Mismatch10:09
- 95. Transfer Learning11:18
- 96. Multi-Task Learning13:00
- 97. End-to-End Deep Learning11:48
- 98. Whether to use End-to-End Learning10:20
