- Neural Networks with Keras Cookbook
- V Kishore Ayyadevara
- 215字
- 2021-07-02 12:46:30
Speeding up the training process using batch normalization
In the previous section on the scaling dataset, we learned that optimization is slow when the input data is not scaled (that is, it is not between zero and one).
The hidden layer value could be high in the following scenarios:
- Input data values are high
- Weight values are high
- The multiplication of weight and input are high
Any of these scenarios can result in a large output value on the hidden layer.
Note that the hidden layer is the input layer to output layer. Hence, the phenomenon of high input values resulting in a slow optimization holds true when hidden layer values are large as well.
Batch normalization comes to the rescue in this scenario. We have already learned that, when input values are high, we perform scaling to reduce the input values. Additionally, we have learned that scaling can also be performed using a different method, which is to subtract the mean of the input and divide it by the standard deviation of the input. Batch normalization performs this method of scaling.
Typically, all values are scaled using the following formula:




Notice that γ and β are learned during training, along with the original parameters of the network.
- DBA攻堅指南:左手Oracle,右手MySQL
- JavaScript 從入門到項目實踐(超值版)
- R語言經典實例(原書第2版)
- 新一代通用視頻編碼H.266/VVC:原理、標準與實現
- 精通搜索分析
- JavaScript從入門到精通(第3版)
- PhpStorm Cookbook
- Mastering ROS for Robotics Programming
- SSM開發實戰教程(Spring+Spring MVC+MyBatis)
- 好好學Java:從零基礎到項目實戰
- Learning JavaScript Data Structures and Algorithms(Second Edition)
- Web程序設計:ASP.NET(第2版)
- Mastering VMware Horizon 7(Second Edition)
- 分布式架構原理與實踐
- Deep Learning for Natural Language Processing