Women in DS (Virtual)

Details

This Meetup wants to celebrate women's contribution in Data Science with high caliber speakers that will showcase their work.

Quick overview of the event: https://medium.com/magiclab-product/meetup-announcement-celebrating-women-in-data-science-with-bumble-and-badoo-a8aa529e2b20?source=friends_link&sk=27b3d2a87c1ee4f0736abfa5fcaf1235\

please register in MagicLab's Zoom Webminar here: https://us02web.zoom.us/webinar/register/9515907646457/WN_CM0X0IHgTYy0vUhQiCLdEA.

This event is open to everyone, we actively encourage a diverse audience as we think will make the conversation more interesting.

Agenda:

18:15 First talk: Efficient ML DevOps - Laura Mitchell (Lead Data Scientist at MagicLab)

18:30:Second talk: How to represent medical terminology for Machine Learning, Claudia Schulz (Lead Researcher at Babylon health)

Abstract:

Bio: Laura is the Lead Data Scientist for MagicLab, a dating app company that produced apps such as Bumble, Badoo and has over 500 million users.

Image detection as a service: how we use APIs and deep learning to support our products In this talk Laura will explain how at MagicLab they created an online image classifier. She will begin by giving an overview of the models they have trained in order to extract a wealth of different information about the content of images. Laura will lead on to introduce the Flask framework and explain how to set up a server which listens on a port and returns a response upon receiving an HTTP request. She will explain how the models can be placed onto the server and from there make predictions on previously unseen images. In the latter part of the talk Laura will introduce the containerised platform Docker and explain how it can be used to create, deploy and run the application.

Second talk: How to represent medical terminology for Machine Learning

Abstract: Machine Learning has many successful application in Medicine. Most of these require some representation of medical terms, usually in the form of vectors. In this talk, I will explain how such vector representations are obtained investigate whether or not they adequately represent medical terminology.

Bio: Claudia Schulz is a lead research scientist at Babylon Health, where she tackles healthcare challenges using NLP, ML, and Knowledge Representation techniques. She has a background in both symbolic AI (PhD from Imperial College London) and NLP / Machine Learning (Postdoctoral Researcher at TU Darmstadt).