Cross Section and Deep Dive into TensorFlow

PLEASE REMEMBER TO REGISTER HERE: https://www.eventbrite.com/e/london-meetup-final-rsvp-cross-section-and-deep-dive-into-tensorflow-tickets-22555927386

Agenda:

7:00 - Doors open. Networking. Beers & Pizza
7:20 - Welcome. Members to vote on the topics of interests for the future meetings.
7:30 - Talk #1. Overview of Tensorflow by Rebecca Murphy, Data Scientist at Ocado Technology
8:00 - Break and Q&A
8:15 - Fireside Chat with Q&A with Armando Vieira and Peter Morgan
8:30 - Talk #2. Deep-Q learning with TensorFlow and PyGame by Daniel Slater, AVP at Bank of America Merrill Lynch
9:00 - Q&A & wrap-up.

Detailed Agenda:

Talk #1: Overview of Tensorflow

What is TensorFlow?
What can we do with TensorFlow?
TensorFlow Mechanics:

• installation
• loading data
• feeding the model
• checkpointing and loading models
  TensorBoard: Visualizing Learning
  Fun TensorFlow applications

Speaker: Rebecca Murphy, Data Scientist at Ocado Technology

Rebecca is a data scientist at Ocado Technology, where she uses deep learning techniques to understand the intricacies of customer choice. She recently completed a PhD at the University of Cambridge, where she spent four years playing with high-power lasers and developed Monte Carlo methods to analyse data from fluorescently labelled protein molecules. In her spare time, Rebecca enjoys running, swimming, cycling and reading. You can find her on twitter (https://twitter.com/rebecca_roisin) or github (https://github.com/rebeccaroisin).

Fireside Chat with Q&A with Armando Vieira and Peter Morgan

Armando Vieira is a Physicist turned into a data scientist. He started working on machine learning since almost 20 years.
From the beginning he was an aficionado of Artificial Neural Networks, having played with them over several academic and industry problems.
Recently he is focused on Deep Neural Networks, especially for unsupervised and semi-supervised learning, mainly applied to Natural Language Processing. He worked as a consultant on several companies and startups and now is a lead data scientist at Bupa.

Peter Morgan is a published author and computer science industry veteran with twenty years’ experience working within the IT industry. Before entering industry, he solved high energy physics problems while enrolled in the PhD program in physics at the University of Massachusetts at Amherst. After spending three years as a Research Associate on an experiment lead by Stanford University to measure the mass of the neutrino, Peter now works as Technical Director at Data Science Partnership a company he cofounded where he oversees business development and helps clients to design and implement their deep learning solutions.

Talk #2: Deep-Q learning with TensorFlow and PyGame

Google deepmind recently broke records for performance running learning agents on Atari games. This talk will look at some of the techniques they use and how to implement it in Tensorflow running PyGame games.

Speaker: Daniel Slater, AVP at Bank of America Merrill Lynch

Daniel Slater is an obsessive programmer who has worked across finance, computer games and e-commerce. Currently working as an AVP at Bank of America Merrill Lynch and doing an MRes in machine learning with a focus on reinforcement learning.