Course curriculum

    1. Course Introduction

    2. Course Overview

    3. Neural Network Defined

    4. Framework for Optimal Learning

    5. Optimal Learning Techniques

    6. Optimal Generalizations Techniques

    7. Optimal Prediction Techniques

    8. Framework Application

    9. Diagnostic Learning Curves

    10. The Fit of the Model

    11. Unrepresentative Dataset

    1. Neural Networks Learn a Mapping Function

    2. Error Surface

    3. Features of the Error Surface

    4. Non-Convex Error Surface

    5. Deep Learning Neural Network Components: Part 1

    6. Deep Learning Neural Network Components: Part 2

    7. Neural Network Model Capacity

    8. Anatomy of a Keras Model

    9. Demo: Case Study on Model Capacity: Part 1

    10. Demo: Case Study on Model Capacity: Part 2

    11. Demo: Case Study on Model Capacity: Part 3

    12. Gradient Precision with Batch Size

    13. Demo: Case Study on Batch Size: Part 1

    14. Demo: Case Study on Batch Size: Part 2

    15. Demo: Case Study on Batch Size: Part 3

    16. Loss Function Defined

    17. Choosing a Loss Function

    18. Demo: Case Study on Regression Loss Functions: Part 1

    19. Demo: Case Study on Regression Loss Functions: Part 2

    20. Demo: Case Study on Binary Classification Loss Functions: Part 1

    21. Demo: Case Study on Binary Classification Loss Functions: Part 2

    22. Demo: Case Study on Binary Classification Loss Functions: Part 3

    23. Demo: Case Study on Multiclass Classification Loss Functions: Part 1

    24. Demo: Case Study on Multiclass Classification Loss Functions: Part 2

    25. Learning Rate Defined

    26. Configuring the Learning Rate

    27. Learning Rate Schedules and Adaptive Learning Rates

    28. Defining Learning Rates in Keras

    29. Demo: Case Study on Learning Rates: Part 1

    30. Demo: Case Study on Learning Rates: Part 2

    31. Demo: Case Study on Learning Rates: Part 3

    32. Demo: Case Study on Learning Rates: Part 4

    33. Data Scaling

    34. Scaling the Input and Ouput Variables

    35. Normalize and Standardize (Rescaling)

    36. Demo: Case Study on Data Scaling: Part 1

    37. Demo: Case Study on Data Scaling: Part 2

    38. Demo: Case Study on Data Scaling: Part 3

    39. Demo: Case Study on Data Scaling: Part 4

    40. Activation Functions and Vanishing Gradients

    41. Rectified Linear Activation Function Defined and Implemented in Python

    42. Rectified Linear Activation Function Defined and Implemented in Python

    43. When ReLU is the Appropriate Choice

    44. Demo: Case Study on Vanishing Gradients: Part 1

    45. Demo: Case Study on Vanishing Gradients: Part 2

    46. Correct Exploding Gradients with Clipping

    47. Gradient Clipping in Keras

    48. Demo: Case Study on Exploding Gradients Part 1

    49. Demo: Case Study on Exploding Gradients Part 2

    50. Batch Normalization

    51. Tips for Applying Batch Normalization

    52. Demo: Case Study on Batch Normalization: Part 1

    53. Demo: Case Study on Batch Normalization: Part 2

    54. Greedy Layer-Wise Pretraining

    55. Demo: Greedy Layer-Wise Pretraining Case Study

    1. The Problem of Overfitting

    2. Reduce Overfitting by Constraining Complexity

    3. Regularization Approaches for Neural Networks

    4. Penalize Large Weights via Regularization

    5. How to Penalize Large Weights

    6. Tips for Using Weight Regularization

    7. Demo: Weight Regularization Case Study: Part 1

    8. Demo: Weight Regularization Case Study: Part 2

    9. Activity Regularization

    10. Encouraging Smaller Activations

    11. Tips for Activity Regularization

    12. Activity Regularization in Keras

    13. Demo: Activity Regularization Case Study

    14. Forcing Small Weights

    15. How to Use a Weight Constraint

    16. Tips for Appling Weight Constraints

    17. Weight Constraints in Keras

    18. Demo: Weight Constraint Case Study

    19. Dropout

    20. Dropout Mechanics

    21. Dropout Tips

    22. Dropout in Keras

    23. Demo: Dropout Case Study

    24. Noise Regularization

    25. How to add Noise

    26. Noise Tips

    27. Adding Noise in Keras

    28. Demo: Noise Regularization Case Study

    1. Ensemble Learning

    2. Ensemble Neural Network Models

    3. Varying the Major Elements

    4. Model Averaging Ensembles

    5. Ensembles in Keras

    6. Demo: Model Averaging Ensemble Case Study: Part 1

    7. Demo: Model Averaging Ensemble Case Study: Part 2

    8. Demo: Model Averaging Ensemble Case Study: Part 3

    9. Weighted Average Ensembles

    10. Demo: Weighted Average Ensemble Case Study: Part 1

    11. Demo: Weighted Average Ensemble Case Study: Part 2

    12. Demo: Weighted Average Ensemble Case Study: Part 3

    13. Demo: Weighted Average Ensemble Case Study: Part 4

    14. Resampling Ensembles

    15. Demo: Resampling Ensemble Case Study: Part 1

    16. Demo: Resampling Ensemble Case Study: Part 2

    17. Demo: Resampling Ensemble Case Study: Part 3

    18. Demo: Resampling Ensemble Case Study: Part 4

    19. Horizontal Voting Ensembles

    20. Demo: Horizontal Ensemble Case Study: Part 1

    21. Demo: Horizontal Ensemble Case Study: Part 2

About this course

  • Free
  • 115 lessons
  • 5 hours of video content