From the course: Building Recommender Systems with Machine Learning and AI

Unlock this course with a free trial

Join today to access over 23,200 courses taught by industry experts.

Handwriting recognition with CNNs

Handwriting recognition with CNNs - Python Tutorial

From the course: Building Recommender Systems with Machine Learning and AI

Start my 1-month free trial Buy for my team

Handwriting recognition with CNNs

“

Let's actually use a CNN and see if we can do a better job at image classification than we've done before using one. Let's actually run a convolutional neural network using Keras. As before, make sure you have your Rexus environment selected in an Anaconda navigator, then launch the Jupiter notebook if you haven't already. and then click on it once it's been uploaded to open it up. We're going to revisit the MNIST handwriting recognition problem here, where we try to classify a bunch of images of people drawing the numbers zero through nine, and see if we can do a better job of it using CNNs. Again, CNNs are better suited to image data in general, especially if you don't know exactly where the feature you're looking for is within your image. So we should expect to get better results here. Let's start by importing all the stuff we need from Keras. We'll import the MNIST data set that we're playing with, the sequential model, so we can assemble our neural network, and then we'll import…

Contents