AI / ML Meetup Series (2 of 4) - Alex Wiltschko Google Brain - TF2.0 & AutoGraph

This is a past event

143 people went

8020 Towers Crescent Dr

8020 Towers Crescent Drive · Vienna

How to find us

Go up to the 2nd floor and head to the 2nd Floor Event Space

Location image of event venue

Details

Details
AI and Machine Learning Enthusiasts!

Your GDG-DC organizer team is so excited to announce a brand new meetup event! Introducing a 4 part series on AI / ML in partnership with the GDG-DC and the Cakes and Tensor's (C&T) Booz Allen meetup groups.

Event Details:
1. September 20th: Algorithms in AI
- Speakers: Jared Sylvester, Booz Allen Hamilton; Megan Yetman, Capital One;
2. October 11th: TF2.0 and AutoGraph : Easier TensorFlow
- Speaker: Alex Wiltschko, Google Brain Team;
3. October 18th: AI Tools and Methods
- Speakers: Dr. Kirk Borne, Booz Allen Hamilton; Tanu Luke, Capital One Eno Team
4. November 15th: MLKit on Android and Machine Learning with NVIDIA hardware team;
- Speakers: Pete Varvarezis, Android Architect @ Capital One; NVIDIA team.

Meetup Series: 2 of 4

Speaker: Alex Wiltschko, Senior Research scientist at Google Brain

Title: TF2.0 and AutoGraph : Easier TensorFlow

Description: We'll talk about two big topics: what TF2.0 will look like at a high level, and AutoGraph, a new TensorFlow feature called "AutoGraph" that writes your graph code for you. AutoGraph automatically converts plain Python code into its TensorFlow equivalents, using source code transformation. For example, instead of tf.cond, and tf.while_loop, users would write imperative-style code with ifs and whiles, and expect it would be converted into its Graph equivalent. We aim to support other convenient Python constructs like lists, recurrent function calls, and list comprehensions, although we will not support the full Python language. Our approach is complementary with the new TensorFlow Eager project and will allow using the imperative style of Eager mode, while retaining the benefits of graph mode. By using automatic code conversion, developers can write code that’s more concise, efficient and robust.

Speaker Bio: Alex Wiltschko is a senior research scientist at Google Brain. He obtained his PhD in neurobiology from Harvard Medical School, where he built new methods for understanding and parsing behavior and body language. He then co-founded Whetlab, an ML-as-a-service company, which was acquired by Twitter in 2015. At Google Brain, Alex works on new tools for machine learning, as well as applying ML to impactful problems in biology.

Agenda:
6:00-6:30 pm - Check-In & Networking (with Food/Drinks)
6:30 pm - Catherine Ordun and Jared Sheehan, Welcome Keynote
6:45 pm - Alex Wiltschko
7:30 pm - Networking and Wrap-up