This video is an overall package to understand Dropout in Neural Network and then implement it in Python from scratch.

Dropout in Neural Network is a regularization technique in Deep Learning to overcome overfitting.

When your training accuracy is very high, but test accuracy is very low, the model highly overfits the training dataset set and struggles to make good predictions on the test dataset.

Overfitting in Deep Learning can be the result of having a very deep neural network or a high number of neurons. With Dropout in Neural Network, we drop certain neurons randomly, and thus, we create a simple network that will generate decision boundary that fits well in both training as well as test dataset.

If our model is not overfitting, then we need not use Dropout Regularization. But when our model is overfitting, only then do we use Dropout in Neural Network.



Download the ASSIGNMENT and Implementation Code: https://github.com/Coding-Lane/Dropout-Regularization



Neural Network in Python from Scratch: https://www.youtube.com/watch?v=vtx1iwmOx10&t=284s&pp=sAQA

Complete Neural Network playlist: https://www.youtube.com/watch?v=mlk0rddP3L4&list=PLuhqtP7jdD8CftMk831qdE8BlIteSaNzD



Overfitting and Underfitting: https://www.youtube.com/watch?v=SOI39DEHGSk&t=0s

Complete Logistic Regression Playlist: https://www.youtube.com/watch?v=U1omz0B9FTw&list=PLuhqtP7jdD8Chy7QIo5U0zzKP8-emLdny

Complete Linear Regression Playlist: https://www.youtube.com/watch?v=nwD5U2WxTdk&list=PLuhqtP7jdD8AFocJuxC6_Zz0HepAWL9cF


Timestamp:
0:00 Agenda
0:54 Overfitting in Deep Learning
1:41 Why Overfitting Occur
2:03 Dropout in Neural Network
4:26 How to Implement Dropout in Neural Network
7:30 Dropout Regularization in Python
13:22 Changing Hyperparameter of Dropout



This is Your Lane to Machine Learning



Subscribe to my channel, because I upload a new Machine Learning video every week : https://www.youtube.com/channel/UCJFAF6IsaMkzHBDdfriY-yQ?sub_confirmation=1