A Hands-on Introduction to Keras, Part 1


Jessica Owensby

Have you every wondered how Facebook facial recognition works? Or how handwriting recognition algorithms work? Convolutional Neural Networks are a special type of Neural Nets that have excellent accuracy in classifying images. We will walk step by step through this sophisticated algorithm to demystify the “magic” going on behind the scenes.

Once we have an understanding of these networks, we will move into how these networks can be trained and even generate our own image classification program using weights from a pre-trained model for Keras.

Keras is capable of running on top of either TensorFlow or Theano. It was developed with a focus on enabling fast experimentation. This talk assumes no prior programming experience with Keras and is geared toward anyone who is interested in getting their feet wet with Neural Networks, but hasn’t yet taken the plunge.

Jumpstart your Machine Learning career with this intro to Keras & Convolutional Neural Networks. By the end of this talk, you’ll have hands-on exposure to Keras, a high-level neural networks library, written in Python, as well as, a roadmap for building Neural Nets that can classify images.