4 pages tagged with "machine learning"

In 2014 Kaggle ran a competition to determine if images contained a dog or a cat. In this series of posts we'll see how easy it is to use Keras to create a 2D convolutional neural network that potentially could have won the contest. In part 1 we used Keras to define a neural network architecture fro… read more

In 2014 Kaggle ran a competition to determine if images contained a dog or a cat. In this series of posts we'll see how easy it is to use Keras to create a 2D convolutional neural network that potentially could have won the contest. In this post we'll see how we can fine tune a network pretrained o… read more

In 2014 Kaggle ran a competition to determine if images contained a dog or a cat. In this series of posts we'll see how easy it is to use Keras to create a 2D convolutional neural network that potentially could have won the contest. We will start with a basic neural network that is 84% accurate at p… read more

In this post we'll use Keras to build the hello world of machine learning, classify a number in an image from the MNIST database of handwritten digits, and achieve ~99% classification accuracy using a convolutional neural network. Much of this is inspired by the book Deep Learning with Python by Fra… read more