CloudAcademy
  1. Home
  2. Training Library
  3. Big Data
  4. Courses
  5. Getting Started With Deep Learning: Convolutional Neural Networks

Pooling Layers

Developed with
Catalit
play-arrow
Start course
Overview
DifficultyBeginner
Duration1h 19m
Students43

Description

In this course, discover convolutions and the convolutional neural networks involved in Data and Machine Learning. Introducing the concept of tensor, which is essential for everything that follows.

Learn to apply the right kind of data such as images. Images store their information in pixels, but you will discover that it is not the value of each pixel that matters.

 

 Learning Objectives

  • Understand how convolutional neural networks are essential to the fundamentals of Data and Machine Learning.

Intended Audience

Transcript

Hello and welcome to this video on pooling layers. In this video we will talk about pooling. A pooling operation reduces the size of the image by discarding some information. For example, max pooling only preserves the maximum value in the patch and stores it in the new image while discarding the value in the other pixels. Also, pooling patches usually do not overlap, so that the size of the image is actually reduced. If we apply pooling to all our output images we end up with smaller 4x4 images that still retain the approximate location of the perfect matches of our filters with the input.

 A pooling layer operates on the hight and the width axis of the data tensor. Similarly, an average pooling layer is the same thing, only instead of using the maximum, we use the average. In conclusion, in this video we talked about pooling and how it reduces the size of the image, preserving the information about the location of the good matches with the filters. So thank you for watching and see you in the next video.

About the Author

Students751
Courses8
Learning paths3

I am a Data Science consultant and trainer. With Catalit I help companies acquire skills and knowledge in data science and harness machine learning and deep learning to reach their goals. With Data Weekends I train people in machine learning, deep learning and big data analytics. I served as lead instructor in Data Science at General Assembly and The Data Incubator and I was Chief Data Officer and co-­founder at Spire, a Y-Combinator-­backed startup that invented the first consumer wearable device capable of continuously tracking respiration and activity. I earned a joint PhD in biophysics at University of Padua and Université de Paris VI and graduated from Singularity University summer program of 2011.