• Урок 1. 00:00:58
    Getting Started - How to Get Help
  • Урок 2. 00:06:05
    Solving Machine Learning Problems
  • Урок 3. 00:09:54
    A Complete Walkthrough
  • Урок 4. 00:02:02
    App Setup
  • Урок 5. 00:02:54
    Problem Outline
  • Урок 6. 00:04:12
    Identifying Relevant Data
  • Урок 7. 00:05:48
    Dataset Structures
  • Урок 8. 00:04:00
    Recording Observation Data
  • Урок 9. 00:04:36
    What Type of Problem?
  • Урок 10. 00:08:24
    How K-Nearest Neighbor Works
  • Урок 11. 00:09:57
    Lodash Review
  • Урок 12. 00:07:17
    Implementing KNN
  • Урок 13. 00:05:54
    Finishing KNN Implementation
  • Урок 14. 00:04:48
    Testing the Algorithm
  • Урок 15. 00:04:13
    Interpreting Bad Results
  • Урок 16. 00:04:06
    Test and Training Data
  • Урок 17. 00:03:49
    Randomizing Test Data
  • Урок 18. 00:03:42
    Generalizing KNN
  • Урок 19. 00:05:19
    Gauging Accuracy
  • Урок 20. 00:03:30
    Printing a Report
  • Урок 21. 00:05:14
    Refactoring Accuracy Reporting
  • Урок 22. 00:11:39
    Investigating Optimal K Values
  • Урок 23. 00:06:37
    Updating KNN for Multiple Features
  • Урок 24. 00:03:57
    Multi-Dimensional KNN
  • Урок 25. 00:09:50
    N-Dimension Distance
  • Урок 26. 00:08:28
    Arbitrary Feature Spaces
  • Урок 27. 00:05:37
    Magnitude Offsets in Features
  • Урок 28. 00:07:33
    Feature Normalization
  • Урок 29. 00:07:15
    Normalization with MinMax
  • Урок 30. 00:04:23
    Applying Normalization
  • Урок 31. 00:07:47
    Feature Selection with KNN
  • Урок 32. 00:06:11
    Objective Feature Picking
  • Урок 33. 00:02:54
    Evaluating Different Feature Values
  • Урок 34. 00:07:28
    Let's Get Our Bearings
  • Урок 35. 00:04:32
    A Plan to Move Forward
  • Урок 36. 00:12:05
    Tensor Shape and Dimension
  • Урок 37. 00:08:19
    Elementwise Operations
  • Урок 38. 00:06:47
    Broadcasting Operations
  • Урок 39. 00:03:48
    Logging Tensor Data
  • Урок 40. 00:05:25
    Tensor Accessors
  • Урок 41. 00:07:47
    Creating Slices of Data
  • Урок 42. 00:05:29
    Tensor Concatenation
  • Урок 43. 00:05:14
    Summing Values Along an Axis
  • Урок 44. 00:07:48
    Massaging Dimensions with ExpandDims
  • Урок 45. 00:04:57
    KNN with Regression
  • Урок 46. 00:04:05
    A Change in Data Structure
  • Урок 47. 00:09:19
    KNN with Tensorflow
  • Урок 48. 00:06:31
    Maintaining Order Relationships
  • Урок 49. 00:08:01
    Sorting Tensors
  • Урок 50. 00:07:44
    Averaging Top Values
  • Урок 51. 00:03:27
    Moving to the Editor
  • Урок 52. 00:10:11
    Loading CSV Data
  • Урок 53. 00:06:11
    Running an Analysis
  • Урок 54. 00:06:27
    Reporting Error Percentages
  • Урок 55. 00:07:34
    Normalization or Standardization?
  • Урок 56. 00:07:38
    Numerical Standardization with Tensorflow
  • Урок 57. 00:04:02
    Applying Standardization
  • Урок 58. 00:08:15
    Debugging Calculations
  • Урок 59. 00:04:01
    What Now?
  • Урок 60. 00:02:40
    Linear Regression
  • Урок 61. 00:04:53
    Why Linear Regression?
  • Урок 62. 00:13:05
    Understanding Gradient Descent
  • Урок 63. 00:10:20
    Guessing Coefficients with MSE
  • Урок 64. 00:05:57
    Observations Around MSE
  • Урок 65. 00:07:13
    Derivatives!
  • Урок 66. 00:11:47
    Gradient Descent in Action
  • Урок 67. 00:05:47
    Quick Breather and Review
  • Урок 68. 00:17:06
    Why a Learning Rate?
  • Урок 69. 00:03:49
    Answering Common Questions
  • Урок 70. 00:04:44
    Gradient Descent with Multiple Terms
  • Урок 71. 00:10:40
    Multiple Terms in Action
  • Урок 72. 00:06:02
    Project Overview
  • Урок 73. 00:05:17
    Data Loading
  • Урок 74. 00:08:33
    Default Algorithm Options
  • Урок 75. 00:03:19
    Formulating the Training Loop
  • Урок 76. 00:09:25
    Initial Gradient Descent Implementation
  • Урок 77. 00:06:53
    Calculating MSE Slopes
  • Урок 78. 00:03:12
    Updating Coefficients
  • Урок 79. 00:10:08
    Interpreting Results
  • Урок 80. 00:07:10
    Matrix Multiplication
  • Урок 81. 00:06:41
    More on Matrix Multiplication
  • Урок 82. 00:06:22
    Matrix Form of Slope Equations
  • Урок 83. 00:09:29
    Simplification with Matrix Multiplication
  • Урок 84. 00:14:02
    How it All Works Together!
  • Урок 85. 00:07:41
    Refactoring the Linear Regression Class
  • Урок 86. 00:08:59
    Refactoring to One Equation
  • Урок 87. 00:06:14
    A Few More Changes
  • Урок 88. 00:03:19
    Same Results? Or Not?
  • Урок 89. 00:08:38
    Calculating Model Accuracy
  • Урок 90. 00:07:45
    Implementing Coefficient of Determination
  • Урок 91. 00:07:48
    Dealing with Bad Accuracy
  • Урок 92. 00:04:37
    Reminder on Standardization
  • Урок 93. 00:03:39
    Data Processing in a Helper Method
  • Урок 94. 00:05:58
    Reapplying Standardization
  • Урок 95. 00:05:37
    Fixing Standardization Issues
  • Урок 96. 00:03:16
    Massaging Learning Rates
  • Урок 97. 00:11:45
    Moving Towards Multivariate Regression
  • Урок 98. 00:07:29
    Refactoring for Multivariate Analysis
  • Урок 99. 00:08:05
    Learning Rate Optimization
  • Урок 100. 00:05:22
    Recording MSE History
  • Урок 101. 00:06:42
    Updating Learning Rate
  • Урок 102. 00:04:18
    Observing Changing Learning Rate and MSE
  • Урок 103. 00:05:22
    Plotting MSE Values
  • Урок 104. 00:04:23
    Plotting MSE History against B Values
  • Урок 105. 00:07:18
    Batch and Stochastic Gradient Descent
  • Урок 106. 00:05:07
    Refactoring Towards Batch Gradient Descent
  • Урок 107. 00:06:03
    Determining Batch Size and Quantity
  • Урок 108. 00:07:49
    Iterating Over Batches
  • Урок 109. 00:05:42
    Evaluating Batch Gradient Descent Results
  • Урок 110. 00:07:38
    Making Predictions with the Model
  • Урок 111. 00:02:28
    Introducing Logistic Regression
  • Урок 112. 00:06:32
    Logistic Regression in Action
  • Урок 113. 00:05:32
    Bad Equation Fits
  • Урок 114. 00:04:32
    The Sigmoid Equation
  • Урок 115. 00:07:48
    Decision Boundaries
  • Урок 116. 00:01:12
    Changes for Logistic Regression
  • Урок 117. 00:05:52
    Project Setup for Logistic Regression
  • Урок 118. 00:04:28
    Importing Vehicle Data
  • Урок 119. 00:04:19
    Encoding Label Values
  • Урок 120. 00:07:09
    Updating Linear Regression for Logistic Regression
  • Урок 121. 00:04:28
    The Sigmoid Equation with Logistic Regression
  • Урок 122. 00:07:46
    A Touch More Refactoring
  • Урок 123. 00:03:28
    Gauging Classification Accuracy
  • Урок 124. 00:05:17
    Implementing a Test Function
  • Урок 125. 00:07:17
    Variable Decision Boundaries
  • Урок 126. 00:05:46
    Mean Squared Error vs Cross Entropy
  • Урок 127. 00:05:09
    Refactoring with Cross Entropy
  • Урок 128. 00:04:37
    Finishing the Cost Refactor
  • Урок 129. 00:03:25
    Plotting Changing Cost History
  • Урок 130. 00:02:20
    Multinominal Logistic Regression
  • Урок 131. 00:05:08
    A Smart Refactor to Multinominal Analysis
  • Урок 132. 00:03:45
    A Smarter Refactor!
  • Урок 133. 00:09:51
    A Single Instance Approach
  • Урок 134. 00:04:40
    Refactoring to Multi-Column Weights
  • Урок 135. 00:04:38
    A Problem to Test Multinominal Classification
  • Урок 136. 00:04:42
    Classifying Continuous Values
  • Урок 137. 00:06:19
    Training a Multinominal Model
  • Урок 138. 00:09:57
    Marginal vs Conditional Probability
  • Урок 139. 00:06:09
    Sigmoid vs Softmax
  • Урок 140. 00:04:43
    Refactoring Sigmoid to Softmax
  • Урок 141. 00:02:37
    Implementing Accuracy Gauges
  • Урок 142. 00:03:16
    Calculating Accuracy
  • Урок 143. 00:02:11
    Handwriting Recognition
  • Урок 144. 00:05:12
    Greyscale Values
  • Урок 145. 00:03:30
    Many Features
  • Урок 146. 00:06:07
    Flattening Image Data
  • Урок 147. 00:05:45
    Encoding Label Values
  • Урок 148. 00:07:27
    Implementing an Accuracy Gauge
  • Урок 149. 00:01:56
    Unchanging Accuracy
  • Урок 150. 00:08:13
    Debugging the Calculation Process
  • Урок 151. 00:06:16
    Dealing with Zero Variances
  • Урок 152. 00:02:37
    Backfilling Variance
  • Урок 153. 00:04:15
    Handing Large Datasets
  • Урок 154. 00:04:51
    Minimizing Memory Usage
  • Урок 155. 00:05:15
    Creating Memory Snapshots
  • Урок 156. 00:06:50
    The Javascript Garbage Collector
  • Урок 157. 00:05:51
    Shallow vs Retained Memory Usage
  • Урок 158. 00:08:30
    Measuring Memory Usage
  • Урок 159. 00:03:15
    Releasing References
  • Урок 160. 00:03:50
    Measuring Footprint Reduction
  • Урок 161. 00:01:31
    Optimization Tensorflow Memory Usage
  • Урок 162. 00:04:41
    Tensorflow's Eager Memory Usage
  • Урок 163. 00:02:49
    Cleaning up Tensors with Tidy
  • Урок 164. 00:03:32
    Implementing TF Tidy
  • Урок 165. 00:03:58
    Tidying the Training Loop
  • Урок 166. 00:01:35
    Measuring Reduced Memory Usage
  • Урок 167. 00:02:36
    One More Optimization
  • Урок 168. 00:02:45
    Final Memory Report
  • Урок 169. 00:04:04
    Plotting Cost History
  • Урок 170. 00:04:19
    NaN in Cost History
  • Урок 171. 00:04:46
    Fixing Cost History
  • Урок 172. 00:01:41
    Massaging Learning Parameters
  • Урок 173. 00:04:28
    Improving Model Accuracy
  • Урок 174. 00:02:07
    Loading CSV Files
  • Урок 175. 00:02:01
    A Test Dataset
  • Урок 176. 00:03:09
    Reading Files from Disk
  • Урок 177. 00:02:55
    Splitting into Columns
  • Урок 178. 00:02:31
    Dropping Trailing Columns
  • Урок 179. 00:03:37
    Parsing Number Values
  • Урок 180. 00:04:20
    Custom Value Parsing
  • Урок 181. 00:05:36
    Extracting Data Columns
  • Урок 182. 00:05:14
    Shuffling Data via Seed Phrase
  • Урок 183. 00:07:45
    Splitting Test and Training
Этот курс находится в платной подписке. Оформи премиум подписку и смотри Machine Learning with Javascript, а также все другие курсы, прямо сейчас!
Премиум