Robin Wieruch 11/16/2017

Improving Gradient Descent in JavaScript

Read Original

This technical article builds on a previous introduction to machine learning in JavaScript, focusing on key improvements for the gradient descent algorithm. It details the critical role of the learning rate (alpha), explaining the consequences of choosing a value that is too high or too low and providing practical guidance on how to select and adjust it by monitoring the cost function.

Improving Gradient Descent in JavaScript

Comments

No comments yet

Be the first to share your thoughts!

Browser Extension

Get instant access to AllDevBlogs from your browser

Top of the Week

No top articles yet