Wolfgang Beyer

This is the second part of my introduction to building an image recognition system with TensorFlow. In the first part we built a softmax classifier to label images from the CIFAR-10 dataset. We achieved an accuracy of around 25-30%. Since there are 10 different and equally likely categories, labeling the images randomly we’d expect an accuracy of 10%. So we’re already a lot better than random, but there’s still plenty of room for improvement.

In this post, I’ll describe how to build a neural network that performs the same task. Let’s see by how much we can increase our prediction accuracy!

This is not a general introduction to Artificial Intelligence, Machine Learning or Deep Learning. There are some great articles covering these topics (for example here or here). It’s also not a discussion about whether AI will enslave humankind or will merely steal all our jobs. You can find plenty of speculation and some premature fearmongering elsewhere. This post is simply a detailed description of how to get started in Machine Learning by building a system that is (somewhat) able to recognize what it sees in an image.

I am currently on a journey to learn about Artificial Intelligence and Machine Learning. And the way I learn best is by not only reading stuff, but by actually building things and getting some hands-on experience. And that’s what this post is about. I want to show you how you can build a system that performs a simple computer vision task: recognizing image content.