1.0Glosarixhttps://glosarix.com/en/Team Glosarixhttps://glosarix.com/en/author/adm_glosarix/rich600338<blockquote class="wp-embedded-content" data-secret="E4AggaEvus"><a href="https://glosarix.com/en/glossary/x-gradient-descent-en/">X-Gradient Descent</a></blockquote><iframe sandbox="allow-scripts" security="restricted" src="https://glosarix.com/en/glossary/x-gradient-descent-en/embed/#?secret=E4AggaEvus" width="600" height="338" title="“X-Gradient Descent” — Glosarix" data-secret="E4AggaEvus" frameborder="0" marginwidth="0" marginheight="0" scrolling="no" class="wp-embedded-content"></iframe><script> /*! This file is auto-generated */ !function(d,l){"use strict";l.querySelector&&d.addEventListener&&"undefined"!=typeof URL&&(d.wp=d.wp||{},d.wp.receiveEmbedMessage||(d.wp.receiveEmbedMessage=function(e){var t=e.data;if((t||t.secret||t.message||t.value)&&!/[^a-zA-Z0-9]/.test(t.secret)){for(var s,r,n,a=l.querySelectorAll('iframe[data-secret="'+t.secret+'"]'),o=l.querySelectorAll('blockquote[data-secret="'+t.secret+'"]'),c=new RegExp("^https?:$","i"),i=0;i<o.length;i++)o[i].style.display="none";for(i=0;i<a.length;i++)s=a[i],e.source===s.contentWindow&&(s.removeAttribute("style"),"height"===t.message?(1e3<(r=parseInt(t.value,10))?r=1e3:~~r<200&&(r=200),s.height=r):"link"===t.message&&(r=new URL(s.getAttribute("src")),n=new URL(t.value),c.test(n.protocol))&&n.host===r.host&&l.activeElement===s&&(d.top.location.href=t.value))}},d.addEventListener("message",d.wp.receiveEmbedMessage,!1),l.addEventListener("DOMContentLoaded",function(){for(var e,t,s=l.querySelectorAll("iframe.wp-embedded-content"),r=0;r<s.length;r++)(t=(e=s[r]).getAttribute("data-secret"))||(t=Math.random().toString(36).substring(2,12),e.src+="#?secret="+t,e.setAttribute("data-secret",t)),e.contentWindow.postMessage({message:"ready",secret:t},"*")},!1)))}(window,document); //# sourceURL=https://glosarix.com/wp-includes/js/wp-embed.min.js </script> Description: X-Gradient Descent is a fundamental optimization algorithm in the training of neural networks, based on minimizing the loss function. This method iteratively adjusts the weights of the neural network using the gradient of the loss function with respect to the current weights. The central idea is that by calculating the gradient, one can determine […]