General Training Session: Practical Deep Learning

Abstract: Gain real deep learning abilities as fast as possible by focusing on the how-to rather than academic theory. You will walk out of this session having built models with human-level performance at visual tasks, and you will understand how to apply these skills to a wide range of new problems. You will build your own models from scratch, as well as using transfer-learning to extend today's highest performing models to new applications. All programming is done with TensorFlow and Keras, but only general Python programming experience is required.

Bio: Dan Becker switched his focus from statistics to machine learning in 2012 after finishing in 2nd place (out of 1353 teams) in the $500,000 Heritage Health Prize on Kaggle.

Since then, Dan has done data science consulting for 6 companies in the Fortune 100, and he has contributed to the TensorFlow and Keras libraries for deep learning. Dan runs Kaggle Learn, which aims to provide the single fastest path to learning advanced data science.