Rice: Created page with "'''Newton's method''' is an alternative to Gradient Descent. In contrast to GD, which uses the first derivative to approach the optimal model, Newton's method adds the ''second derivative'' to converge ''faster''. Newton's method has the drawback of being more computationally expensive due to the need to find the second derivative. $w_j = w_j - a\frac{\frac{\partial l}{\partial w_j}}{\frac{\partial^2 l}{\partial w_j^2}}$ Category:Machine Learning"

2024-04-26T05:24:47Z

Created page with "'''Newton's method''' is an alternative to Gradient Descent. In contrast to GD, which uses the first derivative to approach the optimal model, Newton's method adds the ''second derivative'' to converge ''faster''. Newton's method has the drawback of being more computationally expensive due to the need to find the second derivative. <math> w_j = w_j - a\frac{\frac{\partial l}{\partial w_j}}{\frac{\partial^2 l}{\partial w_j^2}} </math> Category:Machine Learning"

New page

'''Newton's method''' is an alternative to [[Gradient Descent]]. In contrast to GD, which uses the first derivative to approach the optimal model, Newton's method adds the ''second derivative'' to converge ''faster''.

Newton's method has the drawback of being more computationally expensive due to the need to find the second derivative.

<math>
w_j = w_j - a\frac{\frac{\partial l}{\partial w_j}}{\frac{\partial^2 l}{\partial w_j^2}}
</math>

[[Category:Machine Learning]]

Newton's method - Revision history