Skip to content

TensorFlow London Online Meetup: Deep Dive into TensorFlow #29

Photo of Inga Veidmane Millere
Hosted By
Inga Veidmane M.
TensorFlow London Online Meetup: Deep Dive into TensorFlow #29

Details

Welcome to our first online meetup!

Please RSVP to confirm your interest. To join the live session please head to Zoom Webinar: https://zoom.us/webinar/register/WN_Dh6z8KlcSkWCTPSh4LnApg

Talk #1

Speaker: David Mráz, Co-founder at Atheros.ai

Bio: David Mráz is a co-founder at atheros.ai, software architect and machine learning engineer. He was previously a researcher at the Department of Mathematics FCE CTU, but now his focus is solely on helping companies to build AI-driven products. His research interests are especially focused on modern approaches in natural language processing and understanding.

Title: Text classification with transformers in TensorFlow 2

Abstract: The transformer-based language models have been showing promising progress on a number of different natural language processing (NLP) benchmarks. Many model architectures such as BERT, GPT-2, XLNet or recent Turing-NLG pushed the state of the art results on various different NLP tasks. The ability to pre-train the language model on large datasets in an unsupervised way and then finetune on downstream tasks has been one of the biggest reasons for such breakthroughs. The combination of transfer learning methods with large-scale transformer language models is becoming a standard in modern NLP. In this talk, we will make the necessary theoretical introduction to transformer architecture and text classification problem. Then we will demonstrate the fine-tuning process of the pre-trained BERT model for text classification in TensorFlow 2.

Talk #2

Title: TensorFlow.js: Machine Learning in JavaScript

Speaker: Jason Mayes, Senior Developer Advocate for TensorFlow.js at Google (San Francisco)

Bio: Jason combines his knowledge of the technical and creative worlds to solve complex, strategic / technical challenges for Google's largest customers and internal teams. Developing innovative world firsts utilizing the latest technologies and hardware is a key component of his role to rapidly prototype new ideas and consult on project solutions globally. As the DA for TensorFlow.js, he is one of the public faces for TensorFlow.js, helping the wider community to take their first steps and deliver an optimal developer experience for machine learning in JavaScript.

With a background in Computer Science at the University of Bristol, England, where he specialized in reality mining and invisible computing, Jason has been a "hybrid engineer" for over 10 years. Combining his passion for several areas including both front and back end web programming, but also design and user experience, he has worked in many sizes of company from startups (including founding his own) to Google. As a mentor to many, he enjoys sharing his daily discoveries for all his curiosities online, which has attracted a global following of over 350,000.

Social Media Links:
LinkedIn: https://www.linkedin.com/in/creativeTech
Twitter: https://twitter.com/jason_mayes
Facebook: https://facebook.com/JasonDiscovers

Abstract: Join us for a short introductory talk to learn more about machine learning in JavaScript and some of the superpowers you gain by using TensorFlow.js in the browser and beyond.

See you all soon!
TensorFlowLDN

Photo of TensorFlow London group
TensorFlow London
See more events