-
1. Getting Started – How to Get Help.
00:58
-
2. Solving Machine Learning Problems.
06:04
-
3. A Complete Walkthrough.
09:54
-
4. App Setup.
02:01
-
5. Problem Outline.mp4 download
02:53
-
6. Identifying Relevant Data.
04:11
-
7. Dataset Structures.
05:47
-
8. Recording Observation Data.
03:60
-
9. What Type of Problem.mp4 download
04:36
-
1. Introducing Logistic Regression.
02:28
-
10. Encoding Label Values.
04:18
-
11. Updating Linear Regression for Logistic Regression.
07:08
-
12. The Sigmoid Equation with Logistic Regression.
00:00
-
13. A Touch More Refactoring.
07:46
-
14. Gauging Classification Accuracy.
03:27
-
15. Implementing a Test Function.
05:16
-
16. Variable Decision Boundaries.
07:16
-
17. Mean Squared Error vs Cross Entropy.
05:45
-
18. Refactoring with Cross Entropy.
05:08
-
19. Finishing the Cost Refactor.
04:36
-
2. Logistic Regression in Action.
06:31
-
20. Plotting Changing Cost History.
03:24
-
3. Bad Equation Fits.
05:31
-
4. The Sigmoid Equation.
04:31
-
5. Decision Boundaries.
07:47
-
6. Changes for Logistic Regression.
01:12
-
7. Project Setup for Logistic Regression.
05:51
-
9. Importing Vehicle Data.
04:27
-
1. Multinominal Logistic Regression.
02:19
-
10. Sigmoid vs Softmax.
06:08
-
11. Refactoring Sigmoid to Softmax.
00:00
-
12. Implementing Accuracy Gauges.
02:36
-
13. Calculating Accuracy.
03:15
-
2. A Smart Refactor to Multinominal Analysis.
05:07
-
3. A Smarter Refactor!.
00:00
-
4. A Single Instance Approach.
09:50
-
5. Refactoring to Multi-Column Weights.
04:40
-
6. A Problem to Test Multinominal Classification.
04:37
-
7. Classifying Continuous Values.
04:41
-
8. Training a Multinominal Model.
06:19
-
9. Marginal vs Conditional Probability.
09:56
-
1. Handwriting Recognition.
02:10
-
10. Backfilling Variance.
02:36
-
2. Greyscale Values.
05:11
-
3. Many Features.
03:29
-
4. Flattening Image Data.
06:06
-
5. Encoding Label Values.
05:44
-
6. Implementing an Accuracy Gauge.
07:26
-
7. Unchanging Accuracy.
01:55
-
8. Debugging the Calculation Process.
08:13
-
9. Dealing with Zero Variances.
06:15
-
1. Handing Large Datasets.
04:14
-
10. Tensorflow’s Eager Memory Usage
04:40
-
11. Cleaning up Tensors with Tidy.
02:48
-
12. Implementing TF Tidy.
03:31
-
13. Tidying the Training Loop.
03:58
-
14. Measuring Reduced Memory Usage.
00:00
-
15. One More Optimization.
02:35
-
16. Final Memory Report.
02:45
-
17. Plotting Cost History.
00:00
-
18. NaN in Cost History.
00:00
-
19. Fixing Cost History.
04:45
-
2. Minimizing Memory Usage.
00:00
-
20. Massaging Learning Parameters.
00:00
-
21. Improving Model Accuracy.
00:00
-
3. Creating Memory Snapshots.
05:14
-
4. The Javascript Garbage Collector.
00:00
-
5. Shallow vs Retained Memory Usage.
00:00
-
6. Measuring Memory Usage.
08:29
-
7. Releasing References.
03:14
-
8. Measuring Footprint Reduction.
00:00
-
9. Optimization Tensorflow Memory Usage.
01:31
-
1. Loading CSV Files.
00:00
-
10. Splitting Test and Training.
07:44
-
2. A Test Dataset.
02:00
-
3. Reading Files from Disk.
03:08
-
4. Splitting into Columns.
02:54
-
5. Dropping Trailing Columns.
02:30
-
6. Parsing Number Values.
00:00
-
7. Custom Value Parsing.
04:20
-
8. Extracting Data Columns.
00:00
-
9. Shuffling Data via Seed Phrase.
00:00
-
1. How K-Nearest Neighbor Works.
00:00
-
10. Gauging Accuracy.
00:00
-
11. Printing a Report.
03:30
-
12. Refactoring Accuracy Reporting.
00:00
-
13. Investigating Optimal K Values.
11:38
-
14. Updating KNN for Multiple Features.
00:00
-
15. Multi-Dimensional KNN.
03:56
-
16. N-Dimension Distance.
09:50
-
17. Arbitrary Feature Spaces.
08:27
-
18. Magnitude Offsets in Features.
05:36
-
19. Feature Normalization.
07:32
-
2. Lodash Review.
09:56
-
20. Normalization with MinMax.
07:14
-
21. Applying Normalization.
04:22
-
22. Feature Selection with KNN
07:47
-
23. Objective Feature Picking.
06:10
-
24. Evaluating Different Feature Values.
02:53
-
3. Implementing KNN.
07:16
-
4. Finishing KNN Implementation.
00:00
-
5. Testing the Algorithm.
04:47
-
6. Interpreting Bad Results.
04:12
-
7. Test and Training Data.
04:05
-
8. Randomizing Test Data.
03:48
-
9. Generalizing KNN.
03:41
-
1. Let’s Get Our Bearings.
07:27
-
10. Creating Slices of Data.
07:46
-
11. Tensor Concatenation.
05:28
-
12. Summing Values Along an Axis.
05:13
-
13. Massaging Dimensions with ExpandDims.
07:47
-
2. A Plan to Move Forward.
04:31
-
3. Tensor Shape and Dimension.
10:02
-
5. Elementwise Operations.
08:19
-
6. Broadcasting Operations.
06:47
-
8. Logging Tensor Data.
03:47
-
9. Tensor Accessors.
05:24
-
1. KNN with Regression.
04:56
-
10. Reporting Error Percentages.
06:26
-
11. Normalization or Standardization.
07:33
-
12. Numerical Standardization with Tensorflow.
07:37
-
13. Applying Standardization.
04:01
-
14. Debugging Calculations.
08:14
-
15. What Now.
00:00
-
2. A Change in Data Structure.
04:04
-
3. KNN with Tensorflow.
09:18
-
4. Maintaining Order Relationships.
06:30
-
5. Sorting Tensors.
08:00
-
6. Averaging Top Values.
07:44
-
7. Moving to the Editor.
03:26
-
8. Loading CSV Data.
10:10
-
9. Running an Analysis
06:10
-
1. Linear Regression.
02:40
-
10. Answering Common Questions.
03:48
-
11. Gradient Descent with Multiple Terms.
04:43
-
12. Multiple Terms in Action.
10:39
-
2. Why Linear Regression.
04:52
-
3. Understanding Gradient Descent.
13:04
-
4. Guessing Coefficients with MSE.
10:20
-
5. Observations Around MSE.
05:57
-
6. Derivatives!.
07:12
-
7. Gradient Descent in Action.
11:46
-
8. Quick Breather and Review.
05:46
-
9. Why a Learning Rate.
17:05
-
1. Project Overview.
06:01
-
10. More on Matrix Multiplication.
06:40
-
11. Matrix Form of Slope Equations
06:22
-
12. Simplification with Matrix Multiplication.
09:28
-
13. How it All Works Together!.
1414:02
-
2. Data Loading.
00:00
-
3. Default Algorithm Options.
08:32
-
4. Formulating the Training Loop.
03:18
-
5. Initial Gradient Descent Implementation.
09:24
-
6. Calculating MSE Slopes.
06:52
-
7. Updating Coefficients.
03:12
-
8. Interpreting Results.
10:07
-
9. Matrix Multiplication.
00:00
-
1. Refactoring the Linear Regression Class.
07:40
-
10. Reapplying Standardization.
05:57
-
11. Fixing Standardization Issues.
05:36
-
12. Massaging Learning Rates.
03:15
-
13. Moving Towards Multivariate Regression.
11:44
-
14. Refactoring for Multivariate Analysis.
07:28
-
15. Learning Rate Optimization.
08:04
-
16. Recording MSE History.
05:21
-
17. Updating Learning Rate.
06:41
-
2. Refactoring to One Equation.
08:58
-
3. A Few More Changes.
06:13
-
4. Same Results Or Not.
03:19
-
Draft 5. Calculating Model Accuracy
08:37
-
6. Implementing Coefficient of Determination.
07:44
-
7. Dealing with Bad Accuracy.
07:48
-
8. Reminder on Standardization.
04:36
-
9. Data Processing in a Helper Method.
03:38
-
1. Observing Changing Learning Rate and MSE.
04:18
-
2. Refactoring Towards Batch Gradient Descent.
05:21
-
3. Plotting MSE History against B Values.
04:22
-
1. Batch and Stochastic Gradient Descent.
07:17
-
2. Refactoring Towards Batch Gradient Descent.
05:06
-
3. Determining Batch Size and Quantity.
06:02
-
4. Iterating Over Batches.
07:48
-
5. Evaluating Batch Gradient Descent Results.
05:41
-
6. Making Predictions with the Model.
07:37
