Michal Moshkovitz
@ML_Theorist
Followers
984
Following
2K
Statuses
748
Building interpretable and explainable ML models. @ Bosch Center for AI. Previous: postdoc @UCSD, TAU
Joined September 2020
I'm thrilled to share what we're working on—and we need YOUR input! We're mapping the landscape of explainable and interpretable AI, and we need insights from those who use it. Your participation will help us build a comprehensive and reliable overview of the field.
We're conducting a survey on interpretability/explainability. If you are a researcher in XAI or use XAI tools in practice, please help us by filling this short survey! RTs appreciated!
0
4
7
The *Theory of Interpretable AI* seminar is almost one year old! To celebrate, we want to hear from you—what topics would you like covered? 🎈🥳
Our Theory of Interpretable AI ( will soon celebrate its one-year anniversary! 🥳 As we step into our second year, we’d love to hear from you! What papers would you like to see discussed in our seminar in the future? 📚🔍 @tverven @ML_Theorist
0
0
5
Happening now!
Tomorrow, Tuesday, at the Theory of Interpretability seminar: feature attribution methods from the lens of statistics 💻Website: 📷Date: 4 Feb, 4pm CET/ 10am ET @Suuraj
@tverven
@Jere_je_je
0
0
2
Tomorrow, Tuesday, at the Theory of Interpretability seminar: feature attribution methods from the lens of statistics 💻Website: 📷Date: 4 Feb, 4pm CET/ 10am ET @Suuraj
@tverven
@Jere_je_je
The next theory of interpretable AI seminar is Tuesday next week. We will have Jeremias Sulam who present "Testing Semantic Importance via Conditional Independence and Betting" 💻Website: ⏰Date: 4 Feb, 4pm CET/ 10am ET @Suuraj @tverven @Jere_je_je
1
1
8
The next theory of interpretable AI seminar is Tuesday next week. We will have Jeremias Sulam who present "Testing Semantic Importance via Conditional Independence and Betting" 💻Website: ⏰Date: 4 Feb, 4pm CET/ 10am ET @Suuraj @tverven @Jere_je_je
0
1
10
RT @tverven: In case you missed it: here is the recording of @YishayMansour's talk about the ability of decision trees to approximate conce…
0
4
0
Happening now!
The theory of interpretable AI seminar is back after the holiday season! 🎅🤶 Our next talk is next Thursday by Yishay Mansour who will talk about interpretable approximations 💻 Website: ⏰Date: 16 Jan @Suuraj @tverven @YishayMansour
0
0
4
This Thursday (in 3 days), @YishayMansour will discuss interpretable approximations — learning with interpretable models. Is it the same as regular learning? Attend the lecture to find out! 💻 Website: @Suuraj @tverven
The theory of interpretable AI seminar is back after the holiday season! 🎅🤶 Our next talk is next Thursday by Yishay Mansour who will talk about interpretable approximations 💻 Website: ⏰Date: 16 Jan @Suuraj @tverven @YishayMansour
0
3
17
The theory of interpretable AI seminar is back after the holiday season! 🎅🤶 Our next talk is next Thursday by Yishay Mansour who will talk about interpretable approximations 💻 Website: ⏰Date: 16 Jan @Suuraj @tverven @YishayMansour
0
6
23
Next talk Rich Caruana - interpretable models for tablur data
0
0
1
We are kicking off the interpretability workshop with @CynthiaRudin Talking about noise and simplicity
0
0
5
@NeurIPSConf workshop "'Interpretable AI: Past, Present and Future" happening tomorrow 😃
Sunday, next week @NeurIPSConf, come join us for the workshop "'Interpretable AI: Past, Present and Future", we have a great lineup of speakers! @CynthiaRudin @NeelNanda5 #RichCaruana @jxzhangjhu @TongWang
0
1
5
Attended the oral talk @NeurIPSConf "Learning to Grok: Emergence of In-Context Learning & Skill Composition in Modular Arithmetic Tasks" TLDR: Studied how transformers generalize to unseen tasks via simple task of modular addition. Explored the impact of depth & number of tasks
0
0
3
Best part of @NeurIPSConf is meeting friends old and new 😊 DM if you want to grab coffee. We can chat about xai/interpretability or we can talk about foundation models for time series, limitation of transformers and how to improve them
0
0
3