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 Networks 08:29
- 4. Drivers Behind the Rise of Deep Learning 10:22
- 5. Binary Classification in Deep Learning 08:24
- 6. Logistic Regression 06:00
- 7. Logistic Regression Cost Function 08:12
- 8. Gradient Descent 11:24
- 9. Derivatives 07:11
- 10. Derivatives Examples 10:28
- 11. Computation Graph 03:34
- 12. Derivatives with a Computation Graph 14:34
- 13. Logistic Regression Derivatives 06:43
- 14. Gradient Descent on m Training Examples 08:01
- 15. Vectorization 08:05
- 16. More Vectorization Examples 06:20
- 17. Vectorizing Logistic Regression 07:33
- 18. Vectorizing Logistic Regression's Gradient Computation 09:38
- 19. Broadcasting in Python 11:06
- 20. Python-Numpy 06:50
- 21. Jupyter-iPython 03:44
- 22. Logistic Regression Cost Function Explanation 07:15
- 23. Neural Network Overview 04:27
- 24. Neural Network Representation 05:15
- 25. Computing a Neural Network's Output 09:58
- 26. Vectorizing Across Multiple Training Examples 09:06
- 27. Vectorized Implementation Explanation 07:38
- 28. Activation Functions 10:57
- 29. Why Non-Linear Activation Function? 05:36
- 30. Derivatives of Activation Functions 07:58
- 31. Gradient Descent for Neural Networks 09:58
- 32. BackPropagation Intuition (Optional) 15:49
- 33. Random Initialization of Weights 07:58
- 34. Deep L-layer Neural Network 05:52
- 35. Forward Propagation in Deep Networks 07:16
- 36. Getting your Matrix Dimension Right 11:10
- 37. Why DEEP representation? 10:34
- 38. Building Blocks of Deep Neural Network 08:34
- 39. Forward Propagation for Layer L 10:30
- 40. Parameters vs Hyperparameters 07:17
- 41. Brain and Deep Learning 03:18
- 42. Train/Dev/Test sets 12:05
- 43. Bias/ Variance 08:47
- 44. Basic "Recipe" of Machine Learning 06:22
- 45. Regularization 09:43
- 46. Why Regularization reduces Overfitting? 07:10
- 47. Dropout Regularization 09:26
- 48. Why does drop-out work? 07:05
- 49. Other Regularization Methods 08:24
- 50. Normalizing Input 05:31
- 51. Vanishing / Exploding Gradients 06:08
- 52. Weight Initialization for deep networks 06:12
- 53. Numerical Approximation of Gradients 06:36
- 54. Gradient Checking 06:35
- 55. Gradient Checking Implantation Notes 05:19
- 56. Mini Batch Gradient Descent 11:29
- 57. Understanding Mini-Batch Gradient Descent 11:19
- 58. Exponentially Weighted Averages 05:59
- 59. Understanding Exponentially Weighted Averages 09:42
- 60. Bias Correction in Exponentially Weighted Average 04:12
- 61. Gradient Descent with Momentum 09:21
- 62. RMSprop 07:42
- 63. Adam Optimization Algorithm 07:08
- 64. Learning Rate Decay 06:45
- 65. The Problem of Local Optima 05:24
- 66. Tunning Process 07:11
- 67. Right Scale for Hyperparameters 08:51
- 68. Hyperparameters tuning in Practice: Panda vs. Caviar 06:52
- 69. Batch Norm 08:55
- 70. Fitting Batch Norm into a Neural Network 12:56
- 71. Why Does Batch Nom Work? 11:40
- 72. Batch Norm at Test Time 05:47
- 73. Softmax Regression 11:48
- 74. Training a Softmax Classifier 10:08
- 75. Deep Learning Frameworks 04:16
- 76. TensorFlow 16:08
- 77. Why ML Strategy? 02:43
- 78. Orthogonalization 10:39
- 79. Single Number Evaluation Metric 07:17
- 80. Satisfying and Optimizing Metrics 05:59
- 81. train/dev/test distributions 06:36
- 82. Size of dev and test sets 05:40
- 83. When to change dev/test sets and metrics? 11:08
- 84. Why human-level performance? 05:47
- 85. Avoidable Bias 07:00
- 86. Understanding Human-Level Performance 11:12
- 87. Surpassing Human-Level Performance 06:22
- 88. Improving Your Model Performance 06:21
- 89. Carrying Out Error Analysis 10:32
- 90. Cleaning Up Incorrect Labeled Data 13:06
- 91. Build Your First System Quickly, Then Iterate 06:02
- 92. Training and Testing on Different Distributions 10:56
- 93. Bias and Variance with Mismatched data distributions 18:17
- 94. Addressing Data Mismatch 10:09
- 95. Transfer Learning 11:18
- 96. Multi-Task Learning 13:00
- 97. End-to-End Deep Learning 11:48
- 98. Whether to use End-to-End Learning 10:20
Take this course with you
Download the app to continue lessons from your phone anytime.
