Sigmoid Social

Marco 🌳 ZoccaInterested in interpretable ML, particularly for LLMs? eg "causal" interpretability, as in the "OthelloGPT" paper [1]? Let's connect!1. <a href="https://arxiv.org/abs/2210.13382" target="_blank" rel="nofollow noopener" translate="no">https://arxiv.org/abs/2210.13382</a> <a href="https://sigmoid.social/tags/ai" class="mention hashtag" rel="tag">#ai</a> <a href="https://sigmoid.social/tags/machinelearning" class="mention hashtag" rel="tag">#machinelearning</a> <a href="https://sigmoid.social/tags/interpretability" class="mention hashtag" rel="tag">#interpretability</a> <a href="https://sigmoid.social/tags/interpretableml" class="mention hashtag" rel="tag">#interpretableml</a> <a href="https://sigmoid.social/tags/mechanisticinterpretability" class="mention hashtag" rel="tag">#mechanisticinterpretability</a>

Cosima MeyerThis book is golden! (and I think I'll have to read it again because it's so full of information!) For anyone trying to understand their models, Serg Masís' book "Interpretable Machine Learning with <a href="https://mas.to/tags/Python" class="mention hashtag" rel="nofollow noopener" target="_blank">#Python</a>" provides the right mix of theory and practical approaches. It has both a high-level and applied perspective, which I really enjoyed, and gives both practitioners and those new to the field a good and illustrative starting point. <a href="https://mas.to/tags/interpretableml" class="mention hashtag" rel="nofollow noopener" target="_blank">#interpretableml</a>

Cosima MeyerAnd while this is true for any modeling approach, I think it's especially relevant as we move to more complex models. In my experience, interpretability is important not only in making models accessible to the end user but also in the development process as we strive to build fair and reliable models that produce the best results. <a href="https://mas.to/tags/interpretableml" class="mention hashtag" rel="nofollow noopener" target="_blank">#interpretableml</a> <a href="https://mas.to/tags/xai" class="mention hashtag" rel="nofollow noopener" target="_blank">#xai</a> <a href="https://mas.to/tags/datascience" class="mention hashtag" rel="nofollow noopener" target="_blank">#datascience</a> <a href="https://mas.to/tags/python" class="mention hashtag" rel="nofollow noopener" target="_blank">#python</a>

José OramasGreat news, this year <a href="https://sigmoid.social/tags/AIMLAI" class="mention hashtag" rel="tag">#AIMLAI</a> will be held in conjunction with <a href="https://sigmoid.social/tags/ECMLPKDD" class="mention hashtag" rel="tag">#ECMLPKDD</a> 2024. Looking forward to meeting you in Vilnius! <a href="https://sigmoid.social/tags/xai" class="mention hashtag" rel="tag">#xai</a> <a href="https://sigmoid.social/tags/interpretableML" class="mention hashtag" rel="tag">#interpretableML</a> <a href="https://sigmoid.social/tags/explainability" class="mention hashtag" rel="tag">#explainability</a> <a href="https://sigmoid.social/tags/interpretability" class="mention hashtag" rel="tag">#interpretability</a> <a href="https://sigmoid.social/tags/ai" class="mention hashtag" rel="tag">#ai</a> <a href="https://sigmoid.social/tags/ml" class="mention hashtag" rel="tag">#ml</a> @ECMLPKDD @IDLabResearch @imecVlaanderen @UAntwerpen

UKRI AI for Healthcare CentresOn Friday 28 July and Sat 29 July @icmlconfcome and follow presentations by @PFestor@alj_jenkins and @JoshSouthern13<a href="https://sigmoid.social/tags/interpretableML" class="mention hashtag" rel="tag">#interpretableML</a> for health <a href="https://sigmoid.social/tags/GenerativeAI" class="mention hashtag" rel="tag">#GenerativeAI</a> <a href="https://sigmoid.social/tags/GNN" class="mention hashtag" rel="tag">#GNN</a>

Conor O'SullivanMy new article in <a href="https://me.dm/@towardsdatascience" class="u-url mention">@towardsdatascience</a> One of the points is that IML bring DS closer to goal of science - understanding our natural world. This is one of the reasons I’m so attracted to the field. Trying to understand how a model works is 1000x more interesting than simply evaluating it. <a href="https://sigmoid.social/tags/DataScience" class="mention hashtag" rel="tag">#DataScience</a> <a href="https://sigmoid.social/tags/MachineLearning" class="mention hashtag" rel="tag">#MachineLearning</a> <a href="https://sigmoid.social/tags/InterpretableML" class="mention hashtag" rel="tag">#InterpretableML</a> <a href="https://sigmoid.social/tags/XAI" class="mention hashtag" rel="tag">#XAI</a>No paywall link: <a href="https://towardsdatascience.com/data-science-is-not-science-bb95d783697a?source=friends_link&sk=990dff05efbd4c9369c667f7977a23a7" target="_blank" rel="nofollow noopener" translate="no">https://towardsdatascience.com/data-science-is-not-science-bb95d783697a?source=friends_link&sk=990dff05efbd4c9369c667f7977a23a7</a>

José OramasOur <a href="https://sigmoid.social/tags/WACV23" class="mention hashtag" rel="tag">#WACV23</a> paper on the topic of evaluation for model interpretation methods is available online <a href="https://openaccess.thecvf.com/content/WACV2023/html/Behzadi-Khormouji_A_Protocol_for_Evaluating_Model_Interpretation_Methods_From_Visual_Explanations_WACV_2023_paper.html" target="_blank" rel="nofollow noopener" translate="no">https://openaccess.thecvf.com/content/WACV2023/html/Behzadi-Khormouji_A_Protocol_for_Evaluating_Model_Interpretation_Methods_From_Visual_Explanations_WACV_2023_paper.html</a>Congrats to @behzadikhormuji for the good work. <a href="https://sigmoid.social/tags/XAI" class="mention hashtag" rel="tag">#XAI</a> <a href="https://sigmoid.social/tags/Interpretability" class="mention hashtag" rel="tag">#Interpretability</a> <a href="https://sigmoid.social/tags/interpretableml" class="mention hashtag" rel="tag">#interpretableml</a> <a href="https://sigmoid.social/tags/UAntwerp" class="mention hashtag" rel="tag">#UAntwerp</a> <a href="https://sigmoid.social/tags/imec" class="mention hashtag" rel="tag">#imec</a>

Recent searches

Search options

Administered by:

Server stats:

#interpretableml