Member-only story

Gradient Descent Machine Learning Optimization Algorithm from Scratch in Python

Subscribe

Dhiraj K
3 min readAug 24, 2020

Let's discover the fundamentals of Gradient Descent

Introduction:

Gradient descent Machine Learning method is an optimization algorithm that is used to find the local minima of a differentiable function. It can be used in Linear Regression as well as Neural Network.

In the realm of Machine Learning, It is used to find the values of parameters of a differentiable function such that the loss is minimized.

What is Stochastic gradient descent?

Stochastic gradient descent is an optimization algorithm primarily used in machine learning to find the model parameters that represants the best fit. The term “stochastic” refers to outcomes based upon random probability.
While using Gradient Descent, we need to consider all the points in calculating loss and derivative, but in case of Stochastic gradient descent, we use single point, randomly, in calculating the loss function and its derivative .
By considering only one example at a time and following its slope, we can reach a point very close to the actual minimum.

--

--

Dhiraj K
Dhiraj K

Written by Dhiraj K

Data Scientist & Machine Learning Evangelist. I love transforming data into impactful solutions and sharing my knowledge through teaching. dhiraj10099@gmail.com

No responses yet