Gradient Descent is iterative optimization algorithm that finds the least number of functions in machine learning for reducing the cost.
What is Gradient Descent?
It is first-order iterative optimization algorithm for finding the minimum of a function. In machine learning algorithms, we use gradient descent to minimize the cost function. It finds out the best set of parameters for our algorithm.
Classification of Gradient Descent
1. On the basis of data ingestion
- Full Batch Gradient Descent Algorithm
- Stochastic Gradient Descent Algorithm
In full batch gradient descent algorithms, we use whole data at once to compute the gradient, whereas in stochastic we take a sample while computing the gradient.
2. On the basis of differentiation techniques
- First order Differentiation
- Second order Differentiation