@ExplainableNL

Tweeting about Explainable AI in the Netherlands. Account run by @wzuidema (https://xitter.cf/t.co/TyjUIfRiyb) and others. https://xitter.cf/t.co/BMbmDrKBjB

Joined October 2019
  • Tweets251
  • Following218
  • Followers419
5Media
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
3
43
5
263
Excited to see our work featured in the Fortune. Thank you so much, @jeremyakahn!
Jeremy Kahn@jeremyakahn22 Mar 2022
What’s wrong with “explainable" artificial intelligence? Pretty much everything. fortune.com/2022/03/22/ai-ex…

Software vendors are pushing "explainable A.I." that often isn't | Fortune

Researchers sound alarm over explanations used to engender trust in A.I.

fortune.com
1
1
11
explAInable.NL retweeted
Stanford HAI
@StanfordHAI24 Mar 2022
This year's Spring Conference focuses on foundation models, accountable AI, and embodied AI. HAI Associate Director and event co-host @chrmanning explains these key areas and why you should not miss this event: stanford.io/3IxnjdH
8
17
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.
This Post is from an account that no longer exists. Learn more
2
6
And happy that also our work "On genetic programming representations and fitness functions for interpretable dimensionality reduction" made it to @GeccoConf! Preprint: arxiv.org/abs/2203.00528 A short explanation 👇 1/8

On genetic programming representations and fitness functions for...

Dimensionality reduction (DR) is an important technique for data exploration and knowledge discovery. However, most of the main DR methods are either linear (e.g., PCA), do not provide an explicit...

arxiv.org
Marco Virgolin 🇺🇦@MarcoVirgolin24 Mar 2022
Happy to share that our work "Evolvability Degeneration in Multi-Objective Genetic Programming for Symbolic Regression" has been accepted at @GeccoConf! 🥳🪅🍾 Preprint: arxiv.org/abs/2202.06983. A high-level🧵 of what's going on here👇 1/8

Evolvability Degeneration in Multi-Objective Genetic Programming...

Genetic programming (GP) is one of the best approaches today to discover symbolic regression models. To find models that trade off accuracy and complexity, the non-dominated sorting genetic...

arxiv.org
2
2
5
explAInable.NL retweeted
Nils Trost@TrostNils24 Mar 2022
I visualized my last #semantle game with a UMAP of the word embeddings. Here's the result: bp.bleb.li/viewer?p=D5d3y Semantle is a word guessing game by @NovalisDMT where your guesses, unlike in #wordle, are ranked by their similarity in meaning, not spelling, to the secret word.
6
9
51
explAInable.NL retweeted
NL4XAI@NL4XAI21 Mar 2022
📢#MSCAJobAlert Last days to apply to the PhD student position in #AI within @NL4XAI @MSCActions at @citiususc, 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/esr2… @EU_H2020
9
1
11
explAInable.NL retweeted
DIGIT 🇪🇺
@EU_DIGIT24 Mar 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
24
2
21
Replying to @gchrupala
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
1
1
3
This paper analyzing discrete representations in models of spoken language with @bertrand_higy @liekegelderloos and @afraalishahi will appear at #BlackboxNLP #EMNLP2021 arxiv.org/abs/2105.05582

Discrete representations in neural models of spoken language

The distributed and continuous representations used by neural networks are at odds with representations employed in linguistics, which are typically symbolic. Vector quantization has been proposed...

arxiv.org
1
3
15
explAInable.NL retweeted
Yonatan Belinkov@boknilev11 Nov 2021
Replying to @boknilev @sarahookr @anmarasovic
Hot take from @wzuidema : progress in probing classifiers will not come from sophisticated probing techniques but from the hard work of forming better hypotheses.
3
12
explAInable.NL retweeted
Bennie Mols@BennieMols13 Nov 2021
Tof project: @PostNL geeft door #AI ontworpen postzegels uit. Het algoritme werd getraind op basis van een collectie met 1.500 postzegels uit de periode 1852-1920 postnl.nl/over-postnl/pers-n… #PostNL via @postnl
2
4
8
explAInable.NL retweeted
Mark Riedl@mark_riedl16 Nov 2021
“The False Hope of Current Approaches to Explainable AI in Health Care” thelancet.com/journals/landi… Authors: current XAI methods are unlikely to achieve improved patient-level decision support. Advocate to give up. Me: current XAI isn’t ready, need more research before giving up!
4
22
6
123
1/9 ⚠️ AlgorithmWatch was forced to shut down its #Instagram monitoring project after threats from #Facebook! 👉🏻 Read our story: algorithmwatch.org/en/instag… ✍🏻 And sign our open letter to European lawmakers to protect future research on online platforms: algorithmwatch.org/en/defend… 🧵
16
343
102
514
Our new survey on post-hoc interpretability methods for NLP is out! This covers 19 specific interpretability methods, cites more than 100 publications, and took 1 year to write. I'm very happy this is now public, do consider sharing. Read arxiv.org/abs/2108.04840. A thread 🧵 1/6
Table of content. Presented as a 2d-grid with communication approach as rows and what information each method depends on as columns.

ALT Table of content. Presented as a 2d-grid with communication approach as rows and what information each method depends on as columns.

11
128
18
524
Today I will present our paper 'CF-GNNExplainer: Counterfactual Explanations for Graph Neural Networks' at the Algorithmic Recourse Workshop at #ICML2021! From 15-16:30 CET. Hope to see you there! 😃 Joint work w/ amazing co-authors @__alucic, @gtolomei, @mdr and @fabreetseo 🎉
2
29
1
152
explAInable.NL retweeted
Ana Marasović@anmarasovic21 Jul 2021
While developing your new NLP model, how often do you use explainability methods—gradient attribution, attention scores, finding influential training examples, etc—to help you debug (come up with new hypotheses about why your model works or doesn’t work)?
74%Very rarely
18%Occasionally
8%Very often
130 votes • Final results
2
1
2
7
Happening tomorrow! If you are attending @ICML2021, come by our tutorial on Natural-XAI: Explainable AI with Natural Language Explanations, Monday 19th, 8 - 11 a.m PDT / 4 - 7 p.m. BST! @zeynepakata #XAI
Oana-Maria Camburu@oanacamb20 May 2021
Very excited to announce that I will be giving a #Tutorial at #ICML2021 together @zeynepakata, on Natural-XAI: Explainable AI with Natual Language Explanations!
1
21
2
102
It's clear from talking to clinicians that there is no fixed level of "need" for interpretability from ML. Rather, this is something that varies depending on the decision-maker's personal context and the kind of decision they need to make. Full discussion: vanderschaar-lab.com/making-…
4
1
4
Curious to learn about Explainable Artificial Intelligence (XAI)? XAI focuses on different techniques to break the black-box nature of Machine Learning models and produce human-level explanations bit.ly/3paTxDJ #XAI #AI #analytics #data #machinelearning #deeplearning
6
2
Load more