What we're about

This journal club discusses data science papers and is open to all experience levels and specialities. Keeping up with the latest research and methods is important for data scientists and discussions with like-minded individuals are one of the best ways to do this.

Before each meeting, the organisers will choose one or more papers for that meeting from ones suggested by members. To start the meeting, the member then gives a short overview of the papers to spark discussion. It obviously helps if everyone has attempted to read the paper themselves beforehand but it’s not obligatory.

If you want to share your passion for a subject in a friendly environment, giving a presentation is an excellent way to do so. Just send a message to one of the organisers with details. Although many recent papers have been on deep learning, we would also welcome papers from a broader subset of data science and machine learning research or practice, e.g. causal inference, ethics, privacy or graphical models.

Historically the meetings have been in-person but since the covid-19 pandemic we have moved online and a proportion of our meetings may well continue online in the future too.

Upcoming events (1)

Adapting Neural Networks for the Estimation of Treatment Effects

This month we are discussing “Adapting Neural Networks for the Estimation of Treatment Effects” by Shi, et al. on the subject of causal inference. https://arxiv.org/pdf/1906.02120.pdf This paper addresses the use of neural networks for the estimation of treatment effects from observational data. Generally, estimation proceeds in two stages. First, we fit models for the expected outcome and the probability of treatment (propensity score) for each unit. Second, we plug these fitted models into a downstream estimator of the effect. Neural networks are a natural choice for the models in the first step. The question the authors address is: how can we adapt the design and training of the neural networks used in the first step in order to improve the quality of the final estimate of the treatment effect? We also discuss some implementation aspects of their model. Background material: https://www.bradyneal.com/causal-inference-course Details ** This meeting will be online using Zoom ** Please ensure that you install the Zoom app before the meeting in order to join in the discussions. It may also be possible to use the Zoom browser client but please check your audio/video setup in advance. Agenda: - 19:00: Meet up starts with an introduction to the topic - 19:20: Discuss papers in Zoom breakout rooms - 21:00: Close — A note about the Journal Club format: 1. The sessions usually start with a 5-10 minute introduction to the paper by the topic volunteer, followed by splitting into smaller groups to discuss the paper and other materials. We finish the session by coming together for about 15 minutes to discuss what we have learned as a group and ask questions around the room. 2. There is no speaker at Journal Club. One of the community has volunteered their time to suggest the topic and start the session, but most of the discussion comes from within the groups. 3. You will get more benefit from the session if you read the paper or other materials in advance. We try to provide (where we can find them) accompanying blog posts, relevant code and other summaries of the topic to serve as entry points. 4. If you don't have time to do much preparation, please come anyway. You will probably have something to contribute, and even if you just end up following the other discussions, you can still learn a lot. 5. It's OK just to read the blog post or watch the video :)

Past events (50)

Photos (2)