🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

This paper analyzing discrete representations in models of spoken language with @bertrand_higy Lieke Gelderloos and afra alishahi will appear at #BlackboxNLP #EMNLP2021 arxiv.org/abs/2105.05582

@wzuidema Sara Hooker Ana Marasović Hot take from @wzuidema : progress in probing classifiers will not come from sophisticated probing techniques but from the hard work of forming better hypotheses.

Grzegorz Chrupała 🇪🇺🇺🇦 A paper in ICASSP 2020 proposed probing by "audification" of hidden representations in ASR model. They learn a speech synthesizer on top of the ASR representations. They have a nice video of their work here youtu.be/6gtn7H-pWr8

Interesting blogpost on SHAP / feature attribution using Shapley values, by researchers from Dutch medical AI company Pacmed.

#explainableAI #fairness

A team of researchers from Amsterdam and Rome proposes CF-GNNExplainer: an explainability method for the popular Graph Neural Networks. The method iteratively removes edges from the graph, returning the minimal perturbation that leads to a change in prediction.

"Transparency and explainability pertain to the technical domain ... leaving the ethics and epistemology of AI largely disconnected. In this talk, Russo will focus on how to remedy this problem and introduce an epistemology for glass box AI that can explicitly incorporate values"

📢#MSCAJobAlert Last days to apply to the PhD student position in #AI within NL4XAI Marie Skłodowska-Curie Actions at CiTIUS, ES. Join us and work on the following topic: From Grey-box Models to Explainable Models. ⌛️Deadline 31/03/2022 Apply👉nl4xai.eu/open_position/… Horizon 2020

Excited to see our work featured in the Fortune. Thank you so much, Jeremy Kahn!

Interested in Explainable AI and Finance? Check out this opportunity for a Tenure Track Assistant Professor position at the Informatics Institute, University of Amsterdam! Deadline extended to 3 April 2022.

📢Call for contributions to help identify Europe’s most Critical #OpenSourceSoftware ! We urge all national, regional and local public administrations across all EU 27 member states, to participate! Learn more👉europa.eu/!HXxQqp #FOSSEPS #ThinkOpen

And happy that also our work "On genetic programming representations and fitness functions for interpretable dimensionality reduction" made it to GECCO 2025! Preprint: arxiv.org/abs/2203.00528 A short explanation 👇 1/8

This year's Spring Conference focuses on foundation models, accountable AI, and embodied AI. HAI Associate Director and event co-host Christopher Manning explains these key areas and why you should not miss this event: stanford.io/3IxnjdH

Symbolic regression (SR) is the problem of finding an accurate model of the data in the form of a (hopefully elegant) mathematical expression. SR has been thought to be hard and traditionally attempted using evolutionary algorithms. This begs the question: is SR NP-hard? 1/2

Exciting results from StanfordNLP (with D'Oosterlinck from Gent) on Causal Proxies: using symbolic surrogate models for interpreting deep learning, and testing for causality using counterfactual interventions.