IBM Code Bristol is proud to host the Women in Data Science Bristol event, to coincide with the annual Global Women in Data Science (WiDS) Conference held at Stanford University.
The Women in Data Science (WiDS) initiative aims to inspire and educate data scientists worldwide, regardless of gender, and to support women in the field.
Our event has an all-female lineup of speakers and includes various Tech Talks and a panel discussion.
3 pm – 3.10 pm
Introduction – Yamini Rao
3.10 pm – 3.40 pm
Machine Learning for Continuous Integration
Speaker : Kyra Wulffert
Data Scientist | Virgin Media
As more applications move to a DevOps model with Continuous Integration / Continuous Deployment (CI/CD) pipelines, the testing required for this development model to work inevitably generates lots of data. In this talk, we will present our experience training different ML models with the large dataset from the open source OpenStack’s CI system and how this can be leveraged for automated failure identification and analysis.
3.40 pm – 4.10 pm
Time series classification and Representation learning
Speaker : Dr Zahraa Abdallah
Lecturer in Data Science | University of Bristol
Time series classification (TSC) became a topic of great interest in the last few years. Accurate classification of time series can contribute to a variety of problems in a wide range of domains such as signal processing, pattern recognition, spectrum analysis, energy consumption analysis and many others. One main challenge is the diversity of domains where time-series data come from. Thus, there is no “one model that fits all” in TSC.
This talk will focus on robustness in time series classification and representation learning. In particular, we will give an outline of the current work on time series representation which is stimulated by how flies look at the world through “compound eyes” that are made up of thousands of lenses, called ommatidia.
—————————————–Short Break ————————————–
4.20 pm – 4.50 pm
“I don’t trust AI”: the Role of Explainability in Responsible AI
Speaker : Erika Agostinelli
Data Scientist & Project lead | IBM Data Science and AI Elite team
This session will introduce you to the theory of Explainable AI (XAI) and why it is becoming essential in many Data Science projects. From local to global explainers, several XAI techniques and tools such as SHAP, LIME, Contrastive Explanation Methods and What-If-Tool will be presented with concrete code examples in Python.
Bristol, United Kingdom