Covers: theory of Optimization

- How do neural networks learn?

In this video you will learn the basics of gradient decent and how it can be used to train neural nets.

**Gradient Descent**is one of the most used optimization methods to fit our neural networks. It's important because it allows us to calculate the weigths by updating them with the gradients.

In regular Deep Learning Framework you have to define your Optimizer. There are many ways to do this, but first you have to learn the equation that involves weights and gradients.

Fail to play? Open the link directly: https://youtu.be/UwwJLwaqmkQ

Amir Hajian

0 comment

Contributors

- Who is This For ?
- INTERMEDIATE

Click on each of the following **annotated items** to see details.

Resources5/6

VIDEO 1. Loss Functions

- What is the relevance of loss functions for deep learning?

17 minutes

VIDEO 2. Optimization using Gradient Descent - Part 1

- How do neural networks learn?

26 minutes

VIDEO 3. Optimization using Gradient Descent - Part 2

- How do you use gradient descent for parameter updating?

17 minutes

VIDEO 4. Chain Rule, Backpropagation & Autograd

- How else can I train my neural nets?

21 minutes

REPO 5. Hands-on Optimization

- How to implement optimization methods in PyTorch?
- How can we update parameters with Gradient Descent?
- How to implement gradient descent in Pytorch?

30 minutes

RECIPE 6. Understanding BackPropagation

4 hours

0 comment