Tweetovi
- Tweetovi, trenutna stranica.
- Tweetovi i odgovori
- Medijski sadržaj
Blokirali ste korisnika/cu @amt_shrma
Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @amt_shrma
-
Prikvačeni tweet
If you want to learn more about applying causal inference, try out this Python library
@emrek and I built. We've implemented many of the popular methods so that you can focus on the harder causal questions. https://causalinference.gitlab.io/dowhy/#kddhttps://twitter.com/MSFTResearch/status/1031949184562331648 …Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Many challenges still remain. Perhaps the biggest is how to satisfy causal constraints when generating counterfactuals, so that they are actionable. E.g., it is impossible to change one's education without aging. Some preliminary work https://arxiv.org/abs/1912.03277 3/3
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Rather than approximating the model, counterfactuals are promising since they always convey an accurate picture about the ML model. We outline our method for generating multiple diverse CFs in our
#FAT2020 paper: https://arxiv.org/abs/1905.07697 with@ChenhaoTan & Ramaravind MothilalPrikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Excited to release a library for explaining ML models using counterfactual examples. The idea is simple--explain a prediction by the minimal changes that would lead to a different outcome--but turns out generating a diverse set is challenging. https://github.com/microsoft/dice 1/3https://twitter.com/MSFTResearch/status/1222263439369719810 …
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Thank you for attending! For those interested, the full set of slides are at https://causalinference.gitlab.io/kdd-tutorial/ https://twitter.com/Samujjwal_Sam/status/1213755417475444736 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Really like the idea of supplementary analyses
@Susan_Athey.@emrek and I have implemented some of them in our library DoWhy, more to come!https://twitter.com/nathankallus/status/1205944191039094784 …Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Appropos Bengio's talk at
#neurips19, here's a great summary on applying causal reasoning for machine learning problems like generalization and adversarial robustness https://arxiv.org/abs/1911.10500 by@bschoelkopf#causalMLHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Excited to share that
@emrek & I are writing a book on#causalinference in computing systems. Summary: Machine learning needs causality, and causal inference needs ML methods. Here's the 1st chapter: http://causalinference.gitlab.io/ We'll be sharing drafts online,would love your feedbackHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Amit Sharma proslijedio/la je Tweet
Another academic sibling
@SachinPendse presenting his#CSCW2019 talk on cross-cultural differences in online mental health communities' use. Work /w@amt_shrma@TalkLifeApp@MSFTResearchpic.twitter.com/doJA2J3p9m
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Looks like an interesting competition on causal discoveryhttps://twitter.com/sweichwald/status/1177517100333588485 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Amit Sharma proslijedio/la je Tweet
High time to re-evaluate our choices on a daily level. Everything counts!!https://www.insider.com/greta-thunberg-activists-climate-change-who-are-they-2019-9#liza-zhytkova-is-21-she-was-born-in-belarus-but-grew-up-in-the-us-where-she-says-her-interest-in-climate-issues-only-started-within-the-past-year-8 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Amit Sharma proslijedio/la je Tweet
Hiring India-based RAs/interns for 2 @JPAL_SA projects
Price Competition Among Market Vendors (w/ Ben Roth)
https://www.povertyactionlab.org/careers/research-associate-price-competition-amongst-market-vendors-j-pal-south-asia-103051 …
Volunteerism in India (w/ @GarethNellis) https://www.povertyactionlab.org/careers/research-intern-volunteerism-india-j-pal-south-asia-103056 … Retweets welcomed
@econ_raHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Amit Sharma proslijedio/la je Tweet
Microsoft is expanding its fellowship program with the new Microsoft Investigator Fellowship. We're seeking PhD researchers of all disciplines who plan to make an impact through teaching and research using the Microsoft Azure platform. Submit now: https://aka.ms/AA5qt97
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Amit Sharma proslijedio/la je Tweet
We are very excited to announce the 3rd NeurIPS workshop on Machine Learning for the Developing World (ML4D)! This year’s theme is ‘Challenges and Risks’: What can go wrong with ML4D technologies? How do we tackle this?https://sites.google.com/view/ml4d/home
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Amit Sharma proslijedio/la je Tweet
Our day2
@sigchi summer school on HCAI ended with the presentations and discussions on HCML from Munmun De Choudhury (@munmun10), Amit Sharma (@amt_shrma), Kalika Bali (@kalikabali), and the MakerGhat team (@AzraIsmail1 &@Adi_Vish ).#xhcai#hcixb#acmfcapic.twitter.com/PUDPtgHFPN
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Thank you
@nehakumar for organizing this wonderful summer school bringing together HCI and ML. Enjoyed the conversations on human-centered ML. Slides from my talk: https://www.slideshare.net/AmitSharma315/the-impact-of-computing-systems-causal-inference-in-practice …https://twitter.com/nehakumar/status/1154267919724896256 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Yep, and low-resource environments more broadly. Great to see conferences like COMPASS and ICLR happening in Africa this year.https://www.technologyreview.com/s/613848/ai-africa-machine-learning-ibm-google/ …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Really enjoyed listening to
@rayidghani on the@twimlai podcast about machine learning and societal impact. Cool examples on how prediction does not always help with making decisions, and how interpretability and fairness are intertwined with social good.https://twimlai.com/twiml-talk-283-real-world-model-explainability-with-rayid-ghani/ …Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Amit Sharma proslijedio/la je Tweet
Attending the
@DeepIndaba this year? I'm having fun organizing the "Machine Learning in Resource Constrained Environment" deep dive. We have some amazing speakers lined up, and also want to profile work you have done on ML at the edge. Submissions open for spotlight talks!pic.twitter.com/mPTdQD65de
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Amit Sharma proslijedio/la je Tweet
Awesome thread about biotech and causality/correlation.https://twitter.com/JSheltzer/status/1150828437680074752 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Amit Sharma proslijedio/la je Tweet
Our
#DoWhy#causalinference library has an awesome new API, courtesy of@akelleh! Main idea: The do-sampler API transforms a dataframe of observational data into a dataframe that estimates the interventional distribution. Read all about it: https://medium.com/p/introducing-the-do-sampler-for-causal-inference-a3296ea9e78d?source=email-1cdc1cca2f85--writer.postDistributed&sk=d94c0c1f1ed7e74e03c7e17ae6ebad2a …pic.twitter.com/ysRlwiXdpa
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
Čini se da učitavanje traje već neko vrijeme.
Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.