#explainingmachines search results
Referencing Lisa Gitelman @namleti, Hillebrandt: no such thing as „raw data“. #explainingmachines (aw)
Co-constructed, but self-explanatory: the conference break! #explainingmachines #explainingmachines2022
#katharinarohlfing (@unibielefeld), spokesperson of the @trr318, opens the conference #explainingmachines (aw)
@dweinberger (@bkcharvard): Limits of our ability to understand & generalise insights of #machinelearning hold possibility: end of dogma that generals rule about particulars & of delusion that humankind is able to master world by understanding it all (aw) #explainingmachines
@RiederB (@UvA_Amsterdam): „Machine Learning is a bet that the data captures some kind of truth that can then be applied and operalizationalized.“ (aw) #explainingmachines #explainability @trr_318
@FrankPasquale, first speaker of the second day of #explainingmachines, argues for an approach to the complex debate of the right to explanation via an examination of the rules we have set up for accessing data. #debate #xai (aw)
#elenaesposito (@unibielefeld): the issue of responsible #ai is real, however it is distinct from the challenge of explainable ai (aw) #explainingmachines #artificialintelligence #xai @trr_318 #machinelearning #communication #EthicalAI #explanations
Philipp Cimiano @pcimiano shows via medical and sensitivity stress tests how some models are not able to be accountable for the arguments they produce. #explainingmachines #xai #ArtificialIntelligence #MachineLearning (aw)
Hilldebrandt: 1. What matters is incomputable. 2. It can nevertheless be made computable… 3. …in different ways - and that difference matters. E.g., court evaluating likelihood of somebody to reoffend @mireillemoret #explainingmachines (aw)
What is „the real thing“ - the distribution of the data or how we speak about things? @mireillemoret #explainingmachines (aw)
Rieder: Who are we asking to be accountable in #machinelearning? Is it the model? The company? The partners? Who? When we reckon with knowledge deficits we also need to consider structures such as power differentials. #explainingmachines
@pcimiano: Symbolic/rule based approach shows high accountability while subsymbolic approach lacks #accountability and #controllability, even ‘hallucinating‘ about premises. #explainingmachines #AI #xai @trr318 (aw)
Mareille Hilldebrandt @mireillemoret kicks off session 3 with a discussion of „The new #methodenstreit in #machinelearning“ (aw) #explainingmachines (aw)
@pcimiano: Symbolic/rule based approach shows high accountability while subsymbolic approach lacks #accountability and #controllability, even ‘hallucinating‘ about premises. #explainingmachines #AI #xai @trr318 (aw)
Philipp Cimiano @pcimiano shows via medical and sensitivity stress tests how some models are not able to be accountable for the arguments they produce. #explainingmachines #xai #ArtificialIntelligence #MachineLearning (aw)
@FrankPasquale, first speaker of the second day of #explainingmachines, argues for an approach to the complex debate of the right to explanation via an examination of the rules we have set up for accessing data. #debate #xai (aw)
What is „the real thing“ - the distribution of the data or how we speak about things? @mireillemoret #explainingmachines (aw)
Hilldebrandt: 1. What matters is incomputable. 2. It can nevertheless be made computable… 3. …in different ways - and that difference matters. E.g., court evaluating likelihood of somebody to reoffend @mireillemoret #explainingmachines (aw)
Referencing Lisa Gitelman @namleti, Hillebrandt: no such thing as „raw data“. #explainingmachines (aw)
Mareille Hilldebrandt @mireillemoret kicks off session 3 with a discussion of „The new #methodenstreit in #machinelearning“ (aw) #explainingmachines (aw)
Co-constructed, but self-explanatory: the conference break! #explainingmachines #explainingmachines2022
Rieder: Who are we asking to be accountable in #machinelearning? Is it the model? The company? The partners? Who? When we reckon with knowledge deficits we also need to consider structures such as power differentials. #explainingmachines
@RiederB (@UvA_Amsterdam): „Machine Learning is a bet that the data captures some kind of truth that can then be applied and operalizationalized.“ (aw) #explainingmachines #explainability @trr_318
#elenaesposito (@unibielefeld): the issue of responsible #ai is real, however it is distinct from the challenge of explainable ai (aw) #explainingmachines #artificialintelligence #xai @trr_318 #machinelearning #communication #EthicalAI #explanations
@dweinberger (@bkcharvard): Limits of our ability to understand & generalise insights of #machinelearning hold possibility: end of dogma that generals rule about particulars & of delusion that humankind is able to master world by understanding it all (aw) #explainingmachines
#katharinarohlfing (@unibielefeld), spokesperson of the @trr318, opens the conference #explainingmachines (aw)
#katharinarohlfing (@unibielefeld), spokesperson of the @trr318, opens the conference #explainingmachines (aw)
Co-constructed, but self-explanatory: the conference break! #explainingmachines #explainingmachines2022
Referencing Lisa Gitelman @namleti, Hillebrandt: no such thing as „raw data“. #explainingmachines (aw)
@RiederB (@UvA_Amsterdam): „Machine Learning is a bet that the data captures some kind of truth that can then be applied and operalizationalized.“ (aw) #explainingmachines #explainability @trr_318
@dweinberger (@bkcharvard): Limits of our ability to understand & generalise insights of #machinelearning hold possibility: end of dogma that generals rule about particulars & of delusion that humankind is able to master world by understanding it all (aw) #explainingmachines
#elenaesposito (@unibielefeld): the issue of responsible #ai is real, however it is distinct from the challenge of explainable ai (aw) #explainingmachines #artificialintelligence #xai @trr_318 #machinelearning #communication #EthicalAI #explanations
@FrankPasquale, first speaker of the second day of #explainingmachines, argues for an approach to the complex debate of the right to explanation via an examination of the rules we have set up for accessing data. #debate #xai (aw)
Philipp Cimiano @pcimiano shows via medical and sensitivity stress tests how some models are not able to be accountable for the arguments they produce. #explainingmachines #xai #ArtificialIntelligence #MachineLearning (aw)
Something went wrong.
Something went wrong.
United States Trends
- 1. Bama 17.1K posts
- 2. Oklahoma 26.2K posts
- 3. Ty Simpson 3,622 posts
- 4. #UFC322 30.5K posts
- 5. BOOMER SOONER 1,771 posts
- 6. Iowa 19K posts
- 7. Mateer 3,043 posts
- 8. Jungkook 246K posts
- 9. Brent Venables 1,049 posts
- 10. #RollTide 3,177 posts
- 11. #EubankBenn2 30.3K posts
- 12. South Carolina 33.6K posts
- 13. Kline 1,558 posts
- 14. DeBoer 1,336 posts
- 15. Heisman 10.6K posts
- 16. Ryan Williams 1,701 posts
- 17. Arbuckle 1,047 posts
- 18. Talty 1,592 posts
- 19. Georgia Tech 2,649 posts
- 20. Sabatini 1,086 posts