Thread: In this episode of #TheDataExchangePod I speak with @mortendahlcs, research scientist @dropoutlabsai and creator of @tf_encrypted. We began by discussing how he found himself at the intersection of security and machine learning #TensorFlowhttps://thedataexchange.media/the-state-of-privacy-preserving-machine-learning …
-
Prikaži ovu nit
-
2/ Morten described how
@tf_encrypted began, the current state of the project, and how it fits into the broader space of privacy-preserving analytics and machine learning. He notes that current solutions are still too slow for many (near) real-time applications.1 reply 0 proslijeđenih tweetova 1 korisnik označava da mu se sviđaPrikaži ovu nit -
3/ It’s clear that privacy-preserving ML solutions will employ a variety of techniques including cryptography, homomorphic encryption, federated learning, secure aggregation, differential privacy, MPC and more. We discussed these &
@ucbrise’s stack for coopetitive learning (MC2)1 reply 0 proslijeđenih tweetova 2 korisnika označavaju da im se sviđaPrikaži ovu nit
4/ If you are needing a great intro to privacy-preserving analytics and #MachineLearning, I recommend you listen to my conversation with @mortendahlcs. If you have feedback or suggestions for us, fill out the contact form on #TheDataExchangePod site /Endhttps://thedataexchange.media/the-state-of-privacy-preserving-machine-learning …
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.