- Hands-On Mathematics for Deep Learning
- Jay Dawani
- 130字
- 2021-06-18 18:55:19
Chain rule
Let's take an arbitrary function f that takes variables x and y as input, and there is some change in either variable so that . Using this, we can find the change in f using the following:

This leads us to the following equation:

Then, by taking the limit of the function as , we can derive the chain rule for partial derivatives.
We express this as follows:

We now divide this equation by an additional small quantity (t) on which x and y are dependent, to find the gradient along . The preceding equation then becomes this one:

The differentiation rules that we came across earlier still apply here and can be extended to the multivariable case.
推薦閱讀
- 數(shù)據(jù)庫應(yīng)用實戰(zhàn)
- Unity 5.x Game AI Programming Cookbook
- Java Data Science Cookbook
- Ceph源碼分析
- OracleDBA實戰(zhàn)攻略:運維管理、診斷優(yōu)化、高可用與最佳實踐
- 跟老男孩學(xué)Linux運維:MySQL入門與提高實踐
- ZeroMQ
- 基于OPAC日志的高校圖書館用戶信息需求與檢索行為研究
- 金融商業(yè)算法建模:基于Python和SAS
- Flutter Projects
- Oracle數(shù)據(jù)庫管理、開發(fā)與實踐
- Mastering LOB Development for Silverlight 5:A Case Study in Action
- 機器學(xué)習(xí):實用案例解析
- 大數(shù)據(jù)測試技術(shù):數(shù)據(jù)采集、分析與測試實踐(在線實驗+在線自測)
- Access 2010數(shù)據(jù)庫應(yīng)用技術(shù)教程(第二版)