The best version of all adaptive learning rate optimization algorithms

Reducing the aggresive learning rate decay in Adagrad using the twin sibling of Adadelta

Reducing the aggresive learning rate decay in Adagrad

Parameter updates with unique learning rate for each parameter

A more conscience version of Stochastic Gradient Descent with Momentum

Fast convergence using Stochastic Gradient Descent with Momentum

Minimizing cost functions with less data points

Updating the parameters after seeing a subset of the dataset

Linear Regression + Batch Gradient Descent in Python

A mathematical adventure into Gradient Descent

It's about to go down! 👇