Last updated: Feb 7, 2022

Optimization of Neural Network

Learn about different algorithms, architectures, and techniques for optimising neural networks for better prediction and analysis, as well as improving the accuracy of any model.

Gradient Descent with Momentum

This article will focus on the limitations of gradient descent and how momentum overcomes those shortcomings. Finally, we will look into the maths part.

Author Mayank Goyal

0 upvotes

Nesterov Accelerated Gradient EASY

Nesterov Accelerated Gradient (NAG) is an optimization technique that improves gradient descent by adding a momentum term for faster convergence and reduced oscillations.

Author Mohammad Yawar

0 upvotes

What is AdaGrad?

This blog is about AdaGrad. Why it is used, and what is the concept behind it.

Author Mohammad Yawar

0 upvotes

AdaDelta

In this blog, we will review the Gradient Descent algorithm and its drawbacks and the various Optimizers to remove the drawback.

Author Rajkeshav

0 upvotes

RMSProp

This article focuses on the RMSProp optimizer, the reason behind using it, the work and mathematics behind it. Finally at last, we will look into a python implementation.

Author Mayank Goyal

0 upvotes

Adaptive Moment Estimation (ADAM)

In this article, we will learn ADAM (adaptive moment estimation) optimizer. The derivation of ADAM optimizer and implementation of it.

Author soham Medewar

2 upvotes

Limited-Memory Broyden-Fletcher-Goldfarb-Shanno Algorithm

In this article, we will discuss the L-BFGS(Limited-Memory Broyden-Fletcher-Goldfarb-Shanno) Algorithm and its maths.

Author soham Medewar

0 upvotes