6:30 - Doors open. Networking. Beer and Pizza
7:00 - Talk # 1 to be announced soon
7:20 - Q&A break.
7:30 - Image Classification Done Simply using Keras and Tensorflow by Rajiv Shah
8:30 - Q&A break
8:40 - Wrap-up.
Image Classification Done Simply using Keras and Tensorflow by Rajiv Shah
This presentation simplifies the process of building an image classifier using Keras with a TensorFlow backend. The image classifier can be built from hundreds of images (as opposed to tens of thousands sometimes used). The presentation will start with building a simple convolutional network, augmenting the data, using a pretrained network, and finally using transfer learning by modifying the last few layers of a pretrained network.
The presentation will use the classic example of classifying cats and dogs. However, prior to the presentation, a Docker image and instructions will be available so you can bring your own custom dataset and walk through building an image classifier.
Rajiv Shah is a senior data scientist at Caterpillar and an Adjunct Assistant Professor at the University of Illinois at Chicago. He is an active member of the data science community in Chicago with an interest into public policy issues, such as surveillance in Chicago. He has a PhD from the University of Illinois at Urbana Champaign. You find more of his projects at www.rajivshah.com or on twitter @rajcs4.