Blog

Overview We’ll examine data from the Stanford Dogs dataset to attempt building a neural network that can classify dogs by breed. For this purpose, we’ll use Keras with Tensorflow as a backend, all running on Google Colab. After training our network and (hopefully achieving some accuracy) we’ll apply our predictor to some of the dogs in my life. With 120 difference breeds represented in the data set, we should temper our expectations of how accurate our system will be.

My first brush with what could be called machine learning was around 2010 with Kevin Gurney’s Artifical Neural Networks, a slim book that must be sorely outdated by now. In fact, this exposure to the material came to me so early that this book served as my introduction to both trigonmetric functions and differential calculus, yet at the time I had no understanding that this curious object the text called “the derivative” was an integral part of calculus.