We are happy to announce the 9th PyData Cambridge meetup!

Many thanks to Raspberry Pi, who host the group.

Agenda

18:45 - Doors open
19:00 Introduction
19:15 - "Autonomous Economic Agents" by David Minarsch and Diarmid Campbell
19:50 - Interval / snacks provided
20:20 - "ITK for medical image manipulation" by Adam Klimont
21:00 - End (Pub TBA)

Code of Conduct

PyData is dedicated to providing a harassment-free event experience for everyone, regardless of gender, sexual orientation, gender identity, and expression, disability, physical appearance, body size, race, or religion. We do not tolerate harassment of participants in any form.

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 (leah@numfocus.org) or organizers.

"Autonomous Economic Agents" by David Minarsch and Diarmid Campbell
We would like to present our Autonomous Economic Agent framework. This is a simple to understand and efficient set of tools to build intelligent agents that can interact with existing web protocols as well as decentralized ledgers like Fetch.AI Ledger and Ethereum Ledger. The goal of those agents is to generate economic value on their owner’s behalf, for instance by collecting and selling data, trading goods, making predictions and reacting to a changing environment. To demonstrate the utility of the framework we will walk the audience through a concrete example of a car-park-monitoring agent. Such an agent, deployed on a Raspberry Pie, can in real-time monitor the car park or a street-side for available parking spaces and sells that information via the Fetch.AI and Ethereum networks. We will discuss how that, and other similar, applications can generate economic value for owners and users of agents. Both the framework and the sample agents are deployment-ready, cf. https://fetchai.github.io/agents-aea/ for more information.

Diarmid Campbell:
Fetch.AI, Diarmid is developing multi-agent systems to help understand how the Fetch.AI platform can bring value to people's lives.
Diarmid has a bachelor’s degree in Pure Mathematics from Imperial College, London.

David Minarsch:
David currently leads the agent team at Fetch.AI and researches smart markets and the governance of blockchains. David holds a PhD in Applied Game Theory from the University of Cambridge.

Adam Klimont: ITK for medical image manipulation

How to resample a 3D tomography scan with just one line of Python code? What are morphological operations? What are GIPL, NifTi, and VTK files? I will answer these (and more!) questions while talking about the Insight Toolkit (ITK) and its applications in medical imaging.

ITK is a set of highly optimised processing tools for multidimensional images. Think scikit-image, but with multiprocessing C++ backend, and specialised in medical images. Recently, ITK developers have put much effort into making a more Pythonic interface — the upcoming version (5.1) will even allow for passing NumPy arrays as inputs to ITK's methods.

In this talk, I will explain basic ITK usage on real-world examples, and compare its speed and usability with the tools from the SciPy ecosystem. I will also guide you through the somewhat complex and distributed documentation. Finally, I will show how to leverage ITK filters for data augmentation during neural network training.

Bio:
I have a background in experimental laser physics. Half-way through my PhD in the Cavendish Lab I got interested in machine learning and its applications in image analysis. I decided to take a break from academia upon graduating in 2017 and I joined Cydar Medical, where I train and productionise deep learning models for clinical use.

Many thanks to our sponsors: ARM, Enthought, fetch.ai, Illumina, NumFOCUS and Raspberry Pi.