Using machine learning to derive insights from connected data

*** Due to the outbreak of novel coronavirus, if you have travelled to or have transited through China in the last 14 days OR have come into close contact with someone who has a confirmed case of novel coronavirus, please do not attend this event. We will check with our speaker to share his slides with you. Our apologies for any inconveniences caused by this request. ***

This is a joint event with the IEEE ACT Section. The talk will be of 45m presentation plus 15m Q&A. There will also be pre-talk drinks and nibbles from 5pm to 5:30pm, kindly sponsored by M&T Resources.

Topic: Using machine learning to derive insights from connected data
Speaker: Dr. Pantelis Elinas, Data61, CSIRO
Date: Monday 3 February 2020
Venue: Australian National University, Research School of Physics, Link Building (#60), Seminar Room (at level 1), Mills Road, Acton
Agenda:
5:00pm – 5:30pm Networking and Refreshments (pizza, drinks and snacks)
5:30pm – 6:30pm Presentation
6:30pm – 7:00pm Networking and Refreshments
RSVP: https://www.meetup.com/CanberraDataSci/events/267258455/

Map and Parking:

• Please see attached photos, which show the entrance of the School of Physics (ANU) on Mills Road and carparks around. Parking in that area or down the ramp (to the right of the map) are free after 5 pm but very limited (6-7 spots).
• There are parking areas on Garran Road with an indication how to reach the buiding.
• There are also parking spots next to intersection of Mills Rd and Eggleston Rd.
• Please do not park in “Reserved Parking Area” as you might get fined.
• Need help: call Fouad at 0451 046 412

Abstract:
We live in a connected world and generate a vast amount of connected data. Social networks, financial transaction systems, biological networks, and transportation systems are all examples. Machine learning researchers have proposed many new algorithms for tackling the challenge of building predictive models for network-structured data. These algorithms exploit relationships in the data and achieve state-of-the-art results on common tasks such as classification and regression.

In this talk, I will discuss fundamental concepts in modern network analysis and provide an overview of the new and fast developing graph machine learning specialization more generally known as geometric deep learning. Furthermore, I will introduce StellarGraph, an open source graph machine learning Python library under development at CSIRO's Data61. StellarGraph implements many state-of-the-art graph machine learning algorithms and it exposes a clean, consistent and easy-to-use API that integrates smoothly with the Python data science ecosystem. Lastly, I will discuss some of the challenges in graph machine learning especially in regard to practical applications.

Bio:
Dr. Pantelis Elinas is a Senior Research Engineer at CSIRO's Data61. His professional background spans the areas of Computer Science, Robotics and Machine Learning. In the past 15 years, Pantelis has tackled problems in robotics, computer vision, computer graphics, assistive living, and mining automation. Currently, as a member of the Investigative Analytics team at Data61, Pantelis is developing machine learning methods and tools for graph mining and analysis. He enjoys working on interesting problems, sharing knowledge, and developing useful software tools and applications.

Website link:
Meetup: https://www.meetup.com/CanberraDataSci/events/267258455/