Discover and read the best of Twitter Threads about #explainability

Most recents (4)

New article on #websites #classification discussing possible #taxonomy that can be used (IAB, Google, Facebook, etc.) as well as #machinelearning models:…

list of useful resources:
a new telegram channel where will post about #explainableai (#XAI for short):…
there are now many useful libraries available for doing #explainability of #AI models: SHAP, LIME, partial dependence plots PDP. And also the "classical" feature importance.
Our german blog on topic of website #categorizations:
Read 6 tweets
[⛳️Recherche] "Dis, tu m'expliques ... ?": l'explicabilité des algorithmes et de l'#IA en quelques questions, articles de recherche et exemples d'application #openalgo #explainability #thread 👇
📍Comment par le contexte: l'explicabilité est de plus en plus présentée comme un objectif, une qualité (attendue) des systèmes algorithmiques, en particulier l'#IA. Or les techniques les plus performantes sont aussi les moins explicables 🤕
🔥 Les sciences sociales ont beaucoup à raconter sur la notion d'explication. L'étude de Tim Miller (2018) souligne l'importance des contrefactuels: on va chercher à expliquer pourquoi le résultat A plutôt que le résultat B ? (explanations are contrastive)…
Read 19 tweets
Design for relationships, not users, and let people change their mind. More brilliance from @projectsbyif @sarahtgold
@projectsbyif @sarahtgold Changing your mind is an important part of being human! Two things that would simplify #datarights and #explainability for people: variable consent as a service, and data risk profiles, so ppl could automatically opt into services at their preferred level of data-sharing.
@projectsbyif @sarahtgold After all, is it possible to have a right without the ability to meaningfully consent? (@lilianedwards ??)
Read 3 tweets
The #AI task force for Economic Transformation in #India (set up by the Government’s Ministry of Commerce and Industry) released its report last month. Some background (B) and key takeaways (T). 1/n
B1. The vision guiding this report is “AI as a socio economic problem solver at large scale rather than only a booster of economic growth”. 2/n
B2. It seeks to address the role of the Government in the field, answer how #AI can improve quality of life, and identify sectors for AI growth. 3/n
Read 24 tweets

Related hashtags

Did Thread Reader help you today?

Support us! We are indie developers!

This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3.00/month or $30.00/year) and get exclusive features!

Become Premium

Too expensive? Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal Become our Patreon

Thank you for your support!