We are delighted to bring to you Bristol's fourth PyData meetup!
We'd like to thank our generous hosts OVO Energy for providing the venue and also IBM for sponsorship of the food and refreshments.
Expect two 30-minute talks, plus two 5-minute lightning talks, plus community announcements.
*NEW* PRE-MEETUP DEEP LEARNING WORKSHOP "An Intro to Deep Learning with Keras"
===============================
We are hosting an optional, fun and free “pre-meetup” workshop also at Ovo Energy, from 5pm-6:30pm, entitled “An Intro to Deep Learning with Keras” and run by our very own John Sandall.
If you wish to attend please sign up to the separate Eventbrite event via this link: http://bit.ly/pydata-bristol-keras-workshop, and bring your laptop with the pre-requisites installed.
(Only 20 places available)
📊 TALKS
=========
"Controlling Aircraft with Deep Reinforcement Learning" by Gordon Rennie
————————————————————————————————————————
Reinforcement learning is a branch of machine learning in which agents learn how to act in a human-like way: through repeated interactions with their environment. Combining reinforcement learning with deep neural nets has recently enabled exciting advances in the field, such as human-champion level performance in the boardgame Go, control in complex robotics tasks, and defeating teams of professional players in DotA 2. In this talk I will give an overview of reinforcement learning and deep reinforcement learning, and look at some of their applications. As a more concrete example, we will examine my dissertation project where I integrated the open-source flight simulation engine JSBSim into a deep RL system, and trained agents to fly planes – all in Python!
https://www.linkedin.com/in/gordon-rennie/
Mike O'Connor on "Hand pose classification in VR using Tensorflow"
———————————————————————————————————————
I'll be presenting some experiences and lessons learned in using Tensorflow Premade Estimators to prototype a classifier for detecting hand poses from a pair of virtual reality gloves. The talk will be accessible to beginners in machine learning and Tensorflow interested in rapid prototyping of machine learning applications with neural networks.
Bio:
Mike O'Connor (@mikeoconnor0308) is a computer scientist currently pursuing a PhD at the University of Bristol, with research interests in high-performance computing, machine learning and human-computer interaction.
⚡️ LIGHTNING TALKS
=====================
1. Coen de Groot with “Hot off the press - A report from PyCon UK”
With PyData the day after PyCon UK, he will be giving you the highlights from the most data-relevant talks of this five day Python conference.
Coen is a professional software developer with 25+ years experience. A freelance Python developer since 2011, he uses web frameworks (Flask, Django, Zope, Pyramid) as well as “bare-bones” Python.
———————————————————————————————————————
2. Matt Hamilton
"I’m going to talk about some of the recent playing about with machine learning and predicting cryptocurrency prices. And also demo Watson Image Recogniser"
🕖 LOGISTICS
==============
Doors open at 18:30, talks kick off at 19:00 sharp, beers from 21:00. There will be a designated pub to head to afterwards.
We're limited on the number of attendees, so if you realise you can't make it, please unRSVP in good time to free up your place for your fellow community members.
Follow @pydatabristol (https://twitter.com/pydatabristol) for updates on this and future events, as well as announcements and news from both the local and the global data community. See you on the 17th!
📜 CODE OF CONDUCT
=======================
The PyData Code of Conduct governs this meetup (http://pydata.org/code-of-conduct.html). To discuss any issues or concerns relating to the code of conduct or the behavior of anyone at a PyData meetup, please contact NumFOCUS Executive Director Leah Silen ([masked]; [masked]) or the group organizer.