Twitter | Pretraživanje | |
Umang Bhatt
Research Fellow . PhD Student . prev: , . forever: .
315
Tweetovi
399
Pratim
448
Osobe koje vas prate
Tweetovi
Umang Bhatt 4 h
Loving this summary by on work with , , and regarding backwards compatibility, dissonance in model errors, and designing for complementarity Also: good morning, New York :)
Reply Retweet Označi sa "sviđa mi se"
Umang Bhatt 1. velj
Love-hate relationship with Barcelona. PROs: experiencing a mix of urban grunge and rich Spanish history was refreshing; plus was lovely CONs: my laptop bag (and its contents) found a new home, thanks to ladrones. I hope the new owners enjoy my (ex-)machine 😭
Reply Retweet Označi sa "sviđa mi se"
Umang Bhatt 30. sij
Odgovor korisniku/ci @ziebrah
Fascinating, any pointers on where to start in the social sci literature? Is it safe to say that the social context of a decision (or intervention as a result of a model output) in the real world would be a precursor to the need for a justification or explanation?
Reply Retweet Označi sa "sviđa mi se"
Umang Bhatt 30. sij
Odgovor korisniku/ci @ziebrah
Ooo love the hot take. Would you say explanation is a social construct, in most cases?
Reply Retweet Označi sa "sviđa mi se"
Umang Bhatt 30. sij
Odgovor korisniku/ci @SarahEskens @alicexiang
Would love to hear the thoughts of on this, given her legal and statistics superpowers
Reply Retweet Označi sa "sviđa mi se"
Umang Bhatt 30. sij
Odgovor korisniku/ci @adrian_weller @alicexiang
Huge shoutout to as well who helped shape the work all throughout :)
Reply Retweet Označi sa "sviđa mi se"
Umang Bhatt 30. sij
Odgovor korisniku/ci @hannawallach @jingyingyang i 2 ostali
Sooo cute!!! I hope the name came to you at first sight :)
Reply Retweet Označi sa "sviđa mi se"
Umang Bhatt 30. sij
Odgovor korisniku/ci @VaroonMathur @alicexiang
Thanks! Would love your thoughts. Huge shoutout to who helped shape the work all throughout :)
Reply Retweet Označi sa "sviđa mi se"
Umang Bhatt proslijedio/la je tweet
Ayşe Naz Erkan 30. sij
One of my favorite talks at by summarizing the state of explainable machine learning boldly. Paper:
Reply Retweet Označi sa "sviđa mi se"
Umang Bhatt proslijedio/la je tweet
Varoon Mathur 30. sij
Fantastic work by and co. on explainability here at . Can’t wait to dive deeper into this!
Reply Retweet Označi sa "sviđa mi se"
Umang Bhatt proslijedio/la je tweet
linnet taylor 30. sij
explainability is mainly used for internal debugging, its goals are not clearly defined, and it has serious technical limitations. 'we suggest everyone cast doubt on those who are claiming to work with explainability technologies' at
Reply Retweet Označi sa "sviđa mi se"
Umang Bhatt proslijedio/la je tweet
Adrian Weller 30. sij
⁩ presenting recent work at FAT*
Reply Retweet Označi sa "sviđa mi se"
Umang Bhatt proslijedio/la je tweet
Partnership on AI 30. sij
PAI research reveals that, in practice, machine learning explainability techniques fall short of transparency goals (). Presenting at in the Plenary room at 11:20 today, & will discuss key findings:
Reply Retweet Označi sa "sviđa mi se"
Umang Bhatt 27. sij
Nice to see LinkedIn using fair rank aggregation in search and deploying feature importance explanations for engineers during model selection; h/t in the tutorial
Reply Retweet Označi sa "sviđa mi se"
Umang Bhatt 26. sij
Odgovor korisniku/ci @umangsbhatt
Please let me know if you're in town and want to connect: currently interested in all things explainability, uncertainty, and robustness
Reply Retweet Označi sa "sviđa mi se"
Umang Bhatt 26. sij
Odgovor korisniku/ci @PartnershipAI
Will be talking about our paper with on XAI in deployment ()
Reply Retweet Označi sa "sviđa mi se"
Umang Bhatt 26. sij
Looking forward to a fun, productive week in Barcelona for the
Reply Retweet Označi sa "sviđa mi se"
Umang Bhatt 24. sij
Odgovor korisniku/ci @dkaushik96
Gave a huge shoutout to , his policy work, and their joint exciting work on counterfactual datasets from human-in-the-loop learning 💪🏽
Reply Retweet Označi sa "sviđa mi se"
Umang Bhatt 24. sij
Odgovor korisniku/ci @umangsbhatt
**sarcastically** “we should use convnets to detect pneumonia in chest X-rays since ofc deep learning sees 20/20” 😬
Reply Retweet Označi sa "sviđa mi se"
Umang Bhatt 24. sij
Reply Retweet Označi sa "sviđa mi se"