Skip to content

Details

The Digital Developer Conference: Data & AI is 24 hour festival for developers and data scientists to learn from IBM experts, partners, and the worldwide community.
The main conference will delivered on demand from 10 am AEST when all content unlocks and the livestream begins.

Find the main conference page here http://ibm.biz/devcon-ai

Follow hastag #DigDevCon for news on Twitter / Linkedin

*************************************************************

The Digital Developer Conference Europe Regional Sessions will be live-streamed from this event page from Noon BST - https://www.crowdcast.io/e/x037jxsr/1?utm_campaign=Meetup

***********************************************************

Schedule hosted by Yamini Rao https://developer.ibm.com/profiles/yrao/,
Developer Advocate at IBM

Session 1 - Noon BST

Adversarial Robustness Toolbox (ART) - Evasion, Poisoning, Extraction and Inference

The open-source project Adversarial Robustness Toolbox (ART) is a Python library for Machine Learning Security hosted by the Linux Foundation for AI&Data. ART provides tools to support developers and researchers in defending and evaluating machine learning models and AI applications against the adversarial threats of Evasion, Poisoning, Extraction, and Inference. ART supports a wide range of machine learning frameworks, data types and machine learning tasks. This talks will provide and introduction to ART, explain how to contribute to ART and connect with the ART developers, walk through an example of evaluating a classification model against evasion threats and show further resources for advanced applications.

Speaker : Beat Buesser, Research Staff Member IBM https://researcher.watson.ibm.com/researcher/view.php?person=ie-beat.buesser

Session 2 - 13:15 BST

Fitting the COVID Curves

During the early stages of the COVID pandemic there was a lot of discussion about flattening the curve, to prevent overload on our health care system. So what exactly is that curve, and how do you fit it to the raw case report data coming in? We will discuss typical approaches and show you when and how they work. In addition, we will discuss a novel approach to consider the nature of an outbreak, resulting in a time series clustering showing the underlying outbreaks in the aggregated data for a region. Some advanced stuff, but you should be able to follow with a bit of Python, statistics and high school maths.

Speaker : Damiaan Zwietering, IBM Developer Advocate
https://developer.ibm.com/profiles/zwietering/

You may also like