Exponentially Weighted Moving Average or Exponential Weighted Average | Deep Learning

Exponentially Weighted Moving Average or Exponential Weighted Average is a very important concept to understand Optimization in Deep Learning.

It means that as we move forward, we simultaneously calculate the average of the points.

In Exponentially Weighted Moving Average, we consider few points, calculate its approximate weighted average, and then plot the graph. Then consider the next point as we move forward in time, calculate its approximate weighted average of the new set of points, and then again plot the graph and so on.

The catch here is that we are calculating the weighted average, and it means that, we give more weight to some points and less weight to the others.

Optimization in Deep Learning like Momentum, RMSProp, Adam can only be implemented with the help of Exponentially Weighted Moving Average. Thus it is very important to understand it.

In the video, we also understood what is Bias Correction and how to implement Bias Correction in Exponentially Weighted Moving Average.

➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖

✔ Improving Neural Network Playlist:    • Overfitting and Underfitting in Machi...  

➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖

✔ Complete Neural Network Playlist:    • Neural Network python from scratch | ...  

✔ Complete Logistic Regression Playlist:    • Logistic Regression Machine Learning ...  

✔ Complete Linear Regression Playlist:    • How Neural Networks work in Machine L...  

➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖

Timestamp:
0:00 Agenda
1:15 What is Exponentially Weighted Moving Average
3:08 Why it is called Weighted Average
5:20 Effect of Beta on Exponentially Weighted Moving Average
6:51 Bias Correction

➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖

This is Your Lane to Machine Learning ⭐

➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖

Subscribe to my channel, because I upload a new Machine Learning video    / @machinelearningwithjay