Veganism Social

Eric Maugendre<a href="https://social.coop/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#AI</a> <a href="https://social.coop/tags/interpretability" class="mention hashtag" rel="nofollow noopener" target="_blank">#interpretability</a> vs <a href="https://social.coop/tags/explainability" class="mention hashtag" rel="nofollow noopener" target="_blank">#explainability</a> 🧵"The explanations themselves can be difficult to convey to nonexperts, such as end users and line-of-business teams" <a href="https://www.techtarget.com/searchenterpriseai/feature/Interpretability-vs-explainability-in-AI-and-machine-learning" rel="nofollow noopener" translate="no" target="_blank">https://www.techtarget.com/searchenterpriseai/feature/Interpretability-vs-explainability-in-AI-and-machine-learning</a><a href="https://social.coop/tags/AIEthics" class="mention hashtag" rel="nofollow noopener" target="_blank">#AIEthics</a> <a href="https://social.coop/tags/compliance" class="mention hashtag" rel="nofollow noopener" target="_blank">#compliance</a> <a href="https://social.coop/tags/taxonomy" class="mention hashtag" rel="nofollow noopener" target="_blank">#taxonomy</a> <a href="https://social.coop/tags/ethicalAI" class="mention hashtag" rel="nofollow noopener" target="_blank">#ethicalAI</a> <a href="https://social.coop/tags/AIEvaluation" class="mention hashtag" rel="nofollow noopener" target="_blank">#AIEvaluation</a> <a href="https://social.coop/tags/linearRegression" class="mention hashtag" rel="nofollow noopener" target="_blank">#linearRegression</a> <a href="https://social.coop/tags/trust" class="mention hashtag" rel="nofollow noopener" target="_blank">#trust</a> <a href="https://social.coop/tags/neuralNetworks" class="mention hashtag" rel="nofollow noopener" target="_blank">#neuralNetworks</a> <a href="https://social.coop/tags/ML" class="mention hashtag" rel="nofollow noopener" target="_blank">#ML</a> <a href="https://social.coop/tags/governance" class="mention hashtag" rel="nofollow noopener" target="_blank">#governance</a> <a href="https://social.coop/tags/AIgovernance" class="mention hashtag" rel="nofollow noopener" target="_blank">#AIgovernance</a> <a href="https://social.coop/tags/safety" class="mention hashtag" rel="nofollow noopener" target="_blank">#safety</a> <a href="https://social.coop/tags/bias" class="mention hashtag" rel="nofollow noopener" target="_blank">#bias</a>

Eric MaugendreFeature Selection in Python; a script ready to use: <a href="https://johfischer.com/2021/08/06/correlation-based-feature-selection-in-python-from-scratch/" rel="nofollow noopener" translate="no" target="_blank">https://johfischer.com/2021/08/06/correlation-based-feature-selection-in-python-from-scratch/</a><a href="https://hachyderm.io/tags/interpretability" class="mention hashtag" rel="nofollow noopener" target="_blank">#interpretability</a> <a href="https://hachyderm.io/tags/featureSelection" class="mention hashtag" rel="nofollow noopener" target="_blank">#featureSelection</a> <a href="https://hachyderm.io/tags/python" class="mention hashtag" rel="nofollow noopener" target="_blank">#python</a> <a href="https://hachyderm.io/tags/probability" class="mention hashtag" rel="nofollow noopener" target="_blank">#probability</a> <a href="https://hachyderm.io/tags/probabilities" class="mention hashtag" rel="nofollow noopener" target="_blank">#probabilities</a> <a href="https://hachyderm.io/tags/bigData" class="mention hashtag" rel="nofollow noopener" target="_blank">#bigData</a> <a href="https://hachyderm.io/tags/classification" class="mention hashtag" rel="nofollow noopener" target="_blank">#classification</a> <a href="https://hachyderm.io/tags/linearRegression" class="mention hashtag" rel="nofollow noopener" target="_blank">#linearRegression</a> <a href="https://hachyderm.io/tags/regression" class="mention hashtag" rel="nofollow noopener" target="_blank">#regression</a> <a href="https://hachyderm.io/tags/Schusterbauer" class="mention hashtag" rel="nofollow noopener" target="_blank">#Schusterbauer</a> <a href="https://hachyderm.io/tags/inference" class="mention hashtag" rel="nofollow noopener" target="_blank">#inference</a> <a href="https://hachyderm.io/tags/AIDev" class="mention hashtag" rel="nofollow noopener" target="_blank">#AIDev</a>

Eric Maugendre"Feature importance helps in understanding which features contribute most to the prediction"A few lines with <a href="https://hachyderm.io/tags/sklearn" class="mention hashtag" rel="nofollow noopener" target="_blank">#sklearn</a>: <a href="https://mljourney.com/sklearn-linear-regression-feature-importance/" rel="nofollow noopener" translate="no" target="_blank">https://mljourney.com/sklearn-linear-regression-feature-importance/</a> <a href="https://hachyderm.io/tags/interpretability" class="mention hashtag" rel="nofollow noopener" target="_blank">#interpretability</a> <a href="https://hachyderm.io/tags/explainability" class="mention hashtag" rel="nofollow noopener" target="_blank">#explainability</a> <a href="https://hachyderm.io/tags/AIethics" class="mention hashtag" rel="nofollow noopener" target="_blank">#AIethics</a> <a href="https://hachyderm.io/tags/compliance" class="mention hashtag" rel="nofollow noopener" target="_blank">#compliance</a> <a href="https://hachyderm.io/tags/taxonomy" class="mention hashtag" rel="nofollow noopener" target="_blank">#taxonomy</a> <a href="https://hachyderm.io/tags/ethicalAI" class="mention hashtag" rel="nofollow noopener" target="_blank">#ethicalAI</a> <a href="https://hachyderm.io/tags/AIevaluation" class="mention hashtag" rel="nofollow noopener" target="_blank">#AIevaluation</a> <a href="https://hachyderm.io/tags/linearRegression" class="mention hashtag" rel="nofollow noopener" target="_blank">#linearRegression</a> <a href="https://hachyderm.io/tags/featureEngineering" class="mention hashtag" rel="nofollow noopener" target="_blank">#featureEngineering</a>

Eric Maugendre<a href="https://a.gup.pe/u/datadon" class="u-url mention" rel="nofollow noopener" target="_blank">@datadon</a>"The following sections discuss several state-of-the-art interpretable and explainable <a href="https://hachyderm.io/tags/ML" class="mention hashtag" rel="nofollow noopener" target="_blank">#ML</a> methods. The selection of works does not comprise an exhaustive survey of the literature. Instead, it is meant to illustrate the commonest properties and inductive biases behind interpretable models and [black-box] explanation methods using concrete instances." <a href="https://wires.onlinelibrary.wiley.com/doi/full/10.1002/widm.1493#widm1493-sec-0010-title" rel="nofollow noopener" translate="no" target="_blank">https://wires.onlinelibrary.wiley.com/doi/full/10.1002/widm.1493#widm1493-sec-0010-title</a> 🧵<a href="https://hachyderm.io/tags/interpretability" class="mention hashtag" rel="nofollow noopener" target="_blank">#interpretability</a> <a href="https://hachyderm.io/tags/explainability" class="mention hashtag" rel="nofollow noopener" target="_blank">#explainability</a> <a href="https://hachyderm.io/tags/aiethics" class="mention hashtag" rel="nofollow noopener" target="_blank">#aiethics</a> <a href="https://hachyderm.io/tags/compliance" class="mention hashtag" rel="nofollow noopener" target="_blank">#compliance</a> <a href="https://hachyderm.io/tags/taxonomy" class="mention hashtag" rel="nofollow noopener" target="_blank">#taxonomy</a> <a href="https://hachyderm.io/tags/ethicalai" class="mention hashtag" rel="nofollow noopener" target="_blank">#ethicalai</a> <a href="https://hachyderm.io/tags/aievaluation" class="mention hashtag" rel="nofollow noopener" target="_blank">#aievaluation</a> <a href="https://hachyderm.io/tags/linearRegression" class="mention hashtag" rel="nofollow noopener" target="_blank">#linearRegression</a>

Eric MaugendreModel "<a href="https://hachyderm.io/tags/interpretability" class="mention hashtag" rel="nofollow noopener" target="_blank">#interpretability</a> and [black-box] <a href="https://hachyderm.io/tags/explainability" class="mention hashtag" rel="nofollow noopener" target="_blank">#explainability</a>, although not necessary in many straightforward applications, become instrumental when the problem definition is incomplete and in the presence of additional desiderata, such as trust, causality, or fairness."<a href="https://wires.onlinelibrary.wiley.com/doi/full/10.1002/widm.1493" rel="nofollow noopener" translate="no" target="_blank">https://wires.onlinelibrary.wiley.com/doi/full/10.1002/widm.1493</a><a href="https://hachyderm.io/tags/aiethics" class="mention hashtag" rel="nofollow noopener" target="_blank">#aiethics</a> <a href="https://hachyderm.io/tags/compliance" class="mention hashtag" rel="nofollow noopener" target="_blank">#compliance</a> <a href="https://hachyderm.io/tags/taxonomy" class="mention hashtag" rel="nofollow noopener" target="_blank">#taxonomy</a> <a href="https://hachyderm.io/tags/ethicalai" class="mention hashtag" rel="nofollow noopener" target="_blank">#ethicalai</a> <a href="https://hachyderm.io/tags/aievaluation" class="mention hashtag" rel="nofollow noopener" target="_blank">#aievaluation</a>

Jenn Wortman VaughanHeard I should write an <a href="https://sigmoid.social/tags/introduction" class="mention hashtag" rel="nofollow noopener" target="_blank">#introduction</a>? Ok.Hi! I'm Jenn. I do research on <a href="https://sigmoid.social/tags/responsibleAI" class="mention hashtag" rel="nofollow noopener" target="_blank">#responsibleAI</a> at Microsoft Research NYC. I'm in the FATE group and co-chair Microsoft's Aether working group on transparency.My research background is in <a href="https://sigmoid.social/tags/machinelearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#machinelearning</a> theory and algorithmic econ, but since my mid-career crisis I've focused on human-centered approaches to <a href="https://sigmoid.social/tags/transparency" class="mention hashtag" rel="nofollow noopener" target="_blank">#transparency</a>, <a href="https://sigmoid.social/tags/interpretability" class="mention hashtag" rel="nofollow noopener" target="_blank">#interpretability</a>, & <a href="https://sigmoid.social/tags/fairness" class="mention hashtag" rel="nofollow noopener" target="_blank">#fairness</a> of AI.I'm into <a href="https://sigmoid.social/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#AI</a> that augments, rather than replaces, human abilities.<a href="http://www.jennwv.com" rel="nofollow noopener" translate="no" target="_blank">http://www.jennwv.com</a>

Recent searches

Search options

Administered by:

Server stats:

#interpretability