About
The Machine Learning for Health and Well-Being (MLwell) Lab is a research lab at the Bio-Medical Engineering department at Tel-Aviv University. Our vision is to create the technology to allow everyone and everywhere access to personalized medicine and precision psychology that is: (i) effective (ii) respects the biological, cultural and behavioral differences between people (iii) respects privacy and other ethical requirements (iv) affordable. Our mission is to improve the state in the art in machine learning algorithms for personalized medicine and precision psychology.
Our News
Upcoming Event
1st Data-Government conference
Ran Gilad-Bachrach will deliver a short talk as a part of the 1st Data-Government conference in Israel in the Reichman University,
Announcement
Clean up your datasets with dftest
Read the blog post of Atai Ambus on our new tool, dftest, for unit-testing data. This is our contribution to the data centric AI field.
New Paper
A Last Switch Dependent Analysis of Satiation and Seasonality in Bandits
When interacting with humans, boredom/novelty should be considered when selecting content. In this paper, recently presented at AIstats we present a novel version of the multi-armed bandit problem that defines this problem. We present theoretical analysis of the problem and algorithms.
New Paper
PyBryt: auto-assessment and auto-grading for computational thinking
In a new technical report we introduce a new tool for auto-grading and auto-assessment to support the learning of computations thinking skills
Announcement
Congratulations to Amnon Catav for defending his thesis
Congratulations to Amnon Catav for successfully defending his Master's thesis
New Paper
Break your Bandit Routine with LSD Rewards: a Last Switch Dependent Analysis of Satiation and Seasonality
In a new technical report we discuss a version of the multi-armed bandit problem that is designed to delivering interventions to people and takes into account novelty effects.
Announcement
Congratulations to Gon Shoham for defending his thesis
Congratulations to Gon Shoham for successfully defending his Master's thesis
Announcement
Congratulations to Roy Hirsch for defending his thesis
Congratulations to Roy Hirsch for successfully defending his Master's thesis
Announcement
Congratulations to Omri Armstrong for defending his thesis
Congratulations to Omri Armstrong for successfully defending his Master's thesis
New Paper
Marginal Contribution Feature Importance-an Axiomatic Approach for Explaining Data
The paper studies way to assign feature importance in order to gain insights about data appeared in ICML 2021
New Paper
Trees with Attention for Set Prediction Tasks
In a new ICML 2021 paper we shows how decision trees can be applied to data with sets. Empirical results show it is on par and sometimes outperforms deep learning.
New Paper
Robust Model Compression Using Deep Hypotheses
In a paper published in AAAI 2021 we show a new method to compress large models. The method allows compressing across model types such that a big neural network can be compressed to a tree and vice-versa.