Become a member
Sign in
Sri Harsha Gottipati
Sri Harsha Gottipati

Sri Harsha Gottipati

15 Following
14 Followers
  • Profile
  • Claps
  • Highlights

Highlighted by Sri Harsha Gottipati

See more

From Gradient Descent Algorithm and Its Variants by Imad Dabbura

…e function J(w) w.r.t the parameters where the g…e function J(w) w.r.t the parameters where the gradient gives the direction of the steepest ascent. The size of the step we take on each iteration to reach the local minimum is determined by the learning rate α. Therefore, we follow the direction of the slope downhill until we reach a local minimum.

Claps from Sri Harsha Gottipati

See more

Probability concepts explained: Maximum likelihood estimation

Jonny Brooks-Bartlett

Probability concepts explained: Introduction

Jonny Brooks-Bartlett

Overfitting vs. Underfitting: A Complete Example

Will Koehrsen