Covers: theory of Regularization
Estimated time needed to finish: 17 minutes
Questions this item addresses:
  • Why do we need dropouts?
How to use this item?

In this video you will learn about dropouts, how to use them to regularize deep neural networks, and how to implement them in PyTorch

What is DropOut?

Alt text DropOut is a regularization method that helps to prevent Overfitting. You'll understand the method when you watch the video. It's important because currently it is one of the most used methods.

Fail to play? Open the link directly:
Author(s) / creator(s) / reference(s)
Amir Hajian
0 comment

Extracting Features Using Convolution And Regularization

Total time needed: ~4 hours
Feature extraction via convolution kernels
Potential Use Cases
Building a DL architecture for for computer vision model.
Who is This For ?
Click on each of the following annotated items to see details.
VIDEO 1. Mathematics of Convolution
  • Why wee need more than MLP?
  • What is a convolution and kernel?
  • What is a Hann function and how to apply it?
  • What are ConvNets and what is their architecture?
31 minutes
VIDEO 2. Why Convolutions? Sobel & Scharr Filters
  • Why to use Convolutions?
  • What is an image filter?
  • What is image segmentation and how is it done?
  • What convolution does really do?
  • What are two famous and edge detection filters / algorithms?
16 minutes
VIDEO 3. 2D Convolutions, Pooling, and Dilated Convolutions
  • What is pooling and padding?
  • What other 2D convolution techniques do exist?
  • When do we use padding and how?
  • When do we use pooling and how?
  • What are dilated convolutions and how they differ from standard convolutions?
30 minutes
VIDEO 4. Conv-Nets
  • How can I apply Sobel and Scharr Operator on image?
  • What is the difference between Sobel and Scharr Operator and how can I visually compare them?
  • What is a Convolutional Neural Network (CNN)?
  • How can one understand a CNN?
20 minutes
VIDEO 5. Regularization using Dropouts
  • Why do we need dropouts?
17 minutes
REPO 6. Hands-on Convolutional Networks
  • How to implement convnets in PyTorch?
30 minutes
RECIPE 7. Understanding Convolution
40 minutes

Concepts Covered

0 comment