Deep Learning with Tensorflow 2.0

Abstract

Developed by Google and written in python, Tensorflow is the most popular deep learning framework. However, it is not perfect. To improve the developer experience, consolidate functionality, and expand on the ability to be deployed, Tensorflow 2 was developed. As of September 30th 2019, Tensorflow 2 is out of alpha and has been given a full release. This talk will address the motivations behind Tensorflow 2 and how it fixes some of the pain points of its predecessor. I will also include a practical example of how to effectively develop deep learning models using some of Tensorflow 2's features.

About the Speaker

Elliott is a Data Scientist at Blacksky inc., a Virginia Based Geospatial company. For the past 5 years he has worked on developing and productizing several aspects of machine learning, particularly in the areas of computer vision and natural language processing. He is always interested in what is making an impact in the world of understanding data.

Outside of work he attends several local DC meetups and loves to engage with and learn from others in the field.

Agenda

6:30pm – 7:00pm Networking and Refreshments
7:00pm – 7:10pm Introduction, Announcements
7:10pm – 7:40pm Presentation
7:40pm – 7:55pm Q&A
8:00pm – 8:30pm Data Drinks @Tonic (2036 G St NW)