Tom Beer

Tom Beer



I’m a researcher interested in causality, actionability and transportability of machine learning systems. At K Health, I design and develop models for personalised, reliable and accessible healthcare. In my research at Uri Shalit’s lab I devised algorithms for robust causal inference from non-experimental data. I completed an MSc in Data Science and a BSc in Electrical Engineering, both at the Technion. I’m an amateur sourdough baker and handtool woodworker.

Recent Posts

A Simple Hotel Recommender - WIP

Built with LLMs and TripAdvisor reviews

Predicting recipe popularity

For my favorite food blog

Revisiting the bias variance tradeoff

A classical principle in modern times

On the Hazards of Proxies II

Part 2: Prediction models

Publications

Using Deep Networks for Scientific Discovery in Physiological Signals

Deep neural networks (DNN) have shown remarkable success in the classification of physiological signals. In this study we propose a …