Self-trained MA cross! - page 9

[Sergey Golubev]

Neural networks made easy (Part 12): Dropout

Since the beginning of this series of articles, we have already made a big progress in studying various neural network models. But the learning process was always performed without our participation. At the same time, there is always a desire to somehow help the neural network to improve training results, which can also be referred to as the convergence of the neural network. In this article we will consider one of such methods entitled Dropout.

Contents

• Introduction
• 1. Dropout: A Method for Increasing Neural Network Convergence
• 2. Implementation
• 2.1. Creating a New Class for Our Model
• 2.2. Feed-Forward
• 2.3. Feed-Backward
• 2.4. Class Saving and Loading Methods
• 2.5. Changes in the Neural Network Base Classes
• 3. Test
• Conclusion
• References
• Programs Used in the Article

[Sergey Golubev]

Neural networks made easy (Part 13): Batch Normalization

In the previous article, we started considering methods aimed at increasing the convergence of neural networks and got acquainted with the Dropout method, which is used to reduce the co-adaptation of features. Let us continue this topic and get acquainted with the methods of normalization.

Contents

• Introduction
• 1. Theoretical Prerequisites for Normalization
• 2. Implementation
• 2.1. Creating a New Class for Our Model
• 2.2. Feed-Forward
• 2.3. Feed-Backward
• 2.4. Changes in the Neural Network Base Classes
• 3. Testing
• Conclusion
• References
• Programs Used in the Article