Workshop: Deep Learning by Design

Modern design of neural networks in computer vision using design patterns. Covering CNN, AutoEncoders, GANs, Object Detection. Will demonstrate principles using Composable pattern for Automatic Learning. All code examples are in TF 2.0/Keras.
Who is this presentation for?
Junior to advanced data scientists
Prerequisite knowledge:
Python TF 1.X Keras Deep Learning
What you'll learn?
1) How to construct models that are AutoML friendly and guide the search space. 2) General AutoML concepts "under the hood" 3) The TF.Keras functional API for coding models.

Andrew Ferlitsch is an expert on computer vision and deep learning at Google Cloud AI Developer Relations, and formerly a principal research scientist for 20 years at Sharp Corporation of Japan, where he has 115 issued US patents and worked on emerging technologies: telepresence, augmented reality, digital signage, and autonomous vehicles. Currently in his present role, he reaches out to developer communities, corporations and universities, teaching Deep Learning and evangelizing Google's AI technologies.