Tweetovi
- Tweetovi, trenutna stranica.
- Tweetovi i odgovori
- Medijski sadržaj
Blokirali ste korisnika/cu @autreche
Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @autreche
-
If you are at
#amld at EPFL, don't miss the AI & Education track https://appliedmldays.org/tracks/ai-education …. Thrilled to join a great set of speakers to talk about the Memorize algorithm (https://www.pnas.org/content/116/10/3988 …) and our on-going large-scale interventional experiment on personalized learning.Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
My take on "Human-Centric Machine Learning: Feedback loops, Human-AI Collaboration and Strategic Behavior": https://people.mpi-sws.org/~manuelgr/manuelgr-human-centric-ml-2020.pdf …. A talk/lecture on some of my recent work. Tons of opportunities for future work!
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Finally, we experiment with synthetic and real lending data to both illustrate our theoretical findings and show that, under strategic behavior, the policies our algorithm find do much better than deterministic threshold rules (n/n)
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Moreover, under no assumptions on the cost individuals pay to change their features, we develop an iterative search algorithm that is guaranteed to find locally optimal decision policies also in polynomial time (5/n)
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
But, if the cost individuals pay to change their features satisfies a monotonicity assumption, we can narrow down the search for the optimal policy to a family of decision policies with desirable properties. This allows for a polynomial time heuristic search algorithm (4/n)
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Then, we first show that, in general, we cannot expect to find optimal decision policies in polynomial time under strategic behavior and there are cases in which deterministic policies are suboptimal (3/n)
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Individuals may use knowledge, gained by transparency, to invest effort strategically in order to receive a beneficial decision. In our work, we show that this strategic investment of effort by individuals can be cast as an optimal transport problem at a population level (2/n)
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Happy to share our (updated) work on optimal decision making under strategic behavior https://arxiv.org/abs/1905.09239 , which lies in the emerging (super exciting) field of strategic machine learning. This work aims to find decision policies that lead individuals to self-improvement (1/n)
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Manuel Gomez-Rodriguez proslijedio/la je Tweet
There's an important difference between decisions and predictions, especially when it comes to fairness. Check out our
#aistats2020 paper "Fair Decisions Despite Imperfect Predictions" with@autreche@krikamol@bschoelkopf Isabel Valera http://arxiv.org/abs/1902.02979Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Thoughtful, nuanced, and well written article on algorithmic bias vs human bias:https://www.nytimes.com/2019/12/06/business/algorithm-bias-fix.html …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
If you go to
#NeurIPS2019, consider attending our workshop on human-centric ML https://sites.google.com/view/hcml-2019 , we have a terrific set of invited speakers (@kgummadi, Deirdre Mulligan,@Aaroth, Finale Doshi-Velez,@_beenkim), contributed papers and panels!Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Manuel Gomez-Rodriguez proslijedio/la je Tweet
Announcing an exciting new conference: "Foundations of Responsible Computing" (FORC). Here is the call for papers: https://responsiblecomputing.org/forc-2020-call-for-paper/ …. The deadline is February 11, and (if I can say so myself :-) it has an absolutely amazing steering and program committee. 1/
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Great collaboration on a problem in personalized education! New machine learning algorithm, theory, and user study on spaced repetition.https://twitter.com/yisongyue/status/1187747589535477761 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Manuel Gomez-Rodriguez proslijedio/la je Tweet
If you're confused by all the "Robot solves Rubik's cube" reporting / tweeting, this is a good, balanced read: https://www.skynettoday.com/briefs/openai-rubiks-cube … Kudo's to BBC for noting the paper / research has not yet been peer-reviewed. 1/2
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
The Max Planck Institutes for Informatics (Saarbruecken), Software Systems (Saarbruecken and Kaiserslautern), and Security and Privacy (Bochum) invite applications for tenure-track faculty in all areas of computer science!https://cra.org/job/max-planck-society-tenure-track-faculty-positions/ …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Manuel Gomez-Rodriguez proslijedio/la je Tweet
One of the most effective things a government can do to foster an ecosystem of AI startups is to have a National Open Data Strategy. Put all government data behind APIs, sponsor the creation of high-quality public datasets in various domains relevant to local markets & language.
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
"Can a social media user guess what her followers want?" In our new paper, we address this question from a theoretical perspective and then provide practical algorithms to detect strategic posting https://arxiv.org/abs/1909.00440
#research#machinelearning#hcmlHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
We are starting to developed machine learning models especially optimized to work together with humans, under different level of automation. Check out regression under human assistance: https://arxiv.org/abs/1909.02963 . Many more to come!
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Your NeurIPS submission didn’t get it? Consider submitting a short version to the NeurIPS workshop on human-centric ML! https://sites.google.com/view/hcml-2019
#neurips2019#neurips19Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
We have posted the CfPs for the NeurIPS workshops on temporal point processes (https://sites.google.com/view/tpp-neurips-2019 …) and human-centric ML (https://sites.google.com/view/hcml-2019 ) which I help organizing! Consider submitting and spread the voice!
Hvala. 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.