# what is Max Pooling in Convolutional neural network (CNN)

In this tutorial, we will be focusing on max pooling which is the second part of image processing Convolutional neural network (CNN). Before going more future I would suggest taking a look at part one which is Understanding convolutional neural network(CNN).

## Max Pooling in Convolutional neural network (CNN) with example

In the previous article, we took the example of a car.

and then we have changed the image into a matrix which will represent the value of pixels (RGB)

now we will be **understanding Max pooling**,

The process of filling in a pooled feature map differs from the one

This time well place a 2×2 box at the top-left corner and move along the row. For every 4 cells your box stands on, well find the maximum numerical value and insert it into the pooled feature map. , for instance, the box currently contains a group of cells where the maximum value.

Imagine that instead of the four appearing in cell 4×2, it appeared in 3×1. When pooling the feature, we would still end up with 4 as the maximum value from that group, and thus we would get the same result in the pooled version.

This process is what provides the convolutional neural network with the “spatial variance” capability. In addition to that, pooling serves to minimize the size of the images as well as the number of parameters which, in turn, prevents an issue of “overfitting” from coming up.

Overfitting, in a nutshell, is when you create an excessively complex model.

and here we complete max pooling. stay tuned for mar topic in Convolutional neural network (CNN).

### Conclusion of MAx Pooling in CNN

we have covered the following topics in this tutorial

- what is MaxPooling?
- understanding about MaxPooling
- applying on real image

I hope you all enjoyed this tutorial, stay tuned for more valuable content on the convolutional neural network until then I would recommend reading this tutorial (Understanding Artificial Neural network (ANN).

Enjoy learning.

What would have been really good would have been if you could have shown what the image looks like after the Convolution layer and the Max Pooling layer – to give us an understanding of what the process looks Like 🙂 Or did I miss a link?