Scholar

Ian Goodfellow

Ian J. Goodfellow is an American computer scientist, engineer, and executive, most noted for his work on artificial neural networks… more

Ian Goodfellow
H-index: 77
Computer science 96%
Physics 3%

by Yoshua BengioReposted by: Ian Goodfellow

Reposted by: Ian Goodfellow

publichealthaction.bsky.social
Hi Bluesky friends! We're putting together our first monthly newsletter to go out tomorrow, and if you haven't subscribed yet, you should! Sign up on our website: https://publichealthactionnetwork.org/contact/

#COVID #longCOVID #stillcoviding #covidisntover #cleanair #cleanairforall

Reposted by: Ian Goodfellow

Reposted by: Ian Goodfellow

ian-goodfellow.bsky.social
#5YearsLongCovid #HalfADecadeOfNeglect #LongCovidAwarenessDay2025

Reposted by: Ian Goodfellow

ian-goodfellow.bsky.social
Oh, actually it was ~3/15. But all of my own time. I then handed things over to my co-author who did a ~12 minute talk on GANs

Reposted by: Ian Goodfellow

Reposted by: Ian Goodfellow

Reposted by: Ian Goodfellow

ian-goodfellow.bsky.social
I ordered one when orders opened today, don’t have it yet obviously
ian-goodfellow.bsky.social
Sign up for our newsletter!
publichealthaction.bsky.social
Hi Bluesky friends! We're putting together our first monthly newsletter to go out tomorrow, and if you haven't subscribed yet, you should! Sign up on our website: https://publichealthactionnetwork.org/contact/

#COVID #longCOVID #stillcoviding #covidisntover #cleanair #cleanairforall
ian-goodfellow.bsky.social
The recording of the GAN test of time award talk by my co-author David Warde-Farley is now available: neurips.cc/virtual/2024...
NeurIPS Test Of Time Test Of TimeNeurIPS 2024
neurips.cc
ian-goodfellow.bsky.social
My co-authors have completed one of the projects I was working on with them before I went on disability leave. Check out this great explainer thread from @davidlindner.bsky.social
davidlindner.bsky.social
New Google DeepMind safety paper! LLM agents are coming – how do we stop them finding complex plans to hack the reward?

Our method, MONA, prevents many such hacks, *even if* humans are unable to detect them!

Inspired by myopic optimization but better performance – details in🧵

Reposted by: Ian Goodfellow

davidlindner.bsky.social
New Google DeepMind safety paper! LLM agents are coming – how do we stop them finding complex plans to hack the reward?

Our method, MONA, prevents many such hacks, *even if* humans are unable to detect them!

Inspired by myopic optimization but better performance – details in🧵
ian-goodfellow.bsky.social
Another more specific way people can help: does anyone know if it’s safe to take betahistine if I have MCAS? And does taking antihistamines make betahistine ineffective?
ian-goodfellow.bsky.social
Posting a call for help: does anyone know of a good way to simultaneously treat both POTS and Ménière’s disease? Please contact me if you’re either a clinician with experience doing this or a patient who has found a good solution. Context in thread

References

Fields & subjects

Updated 1m