
AI + Neuro @DeepMind | Ph.D @PrincetonNeuro | ex @ptoncompmemlab. Opinions my own.
London, England
Joined March 2012
- Tweets264
- Following1.2K
- Followers506
- Likes1.9K
Replying to @vuecinemas
@vuecinemas Harrow checking in! Apparently, prices are a state secret here. Just two combo options on repeat with no menu. How's a person supposed to know if they're getting fleeced? 🤔 This is cinema 101, folks.
36
Can you help me identify this robot? I haven't been able to figure it out just from this silhouette. I need to give a presentation to my daughter about the robots on my t-shirt. Thanks!
3
10 months ago: Galaxy watch 4 released w/o flagship feature
2 weeks ago: Update finally adds flagship feature but causes watch to constantly need factory resetting if enabled. No fix yet.
Now: Galaxy watch 5 will have blah blah blah
The gadget upgrade treadmill is disgusting.
1
It's almost surely unintentional that this mistake is in the author's favor. Nonetheless, it further erodes my confidence in the current ML publishing environment.
Happy Friday the 13th!! Here's a little script/calendar to help you keep track github.com/ElPiloto/friday_t…
Really cool work and dataset, but you get a bunch of little kids when you sort by controversially attractive. What's going on here? Are people misunderstanding the prompt or trolling?
This Post is from an account that no longer exists. Learn more
Replying to @debyeeneuro
You're doing great and anyone who tells you otherwise can take it up with the Fitbit!
1
I got dissed by ML so bad last night. I had this painful ingrown hair on the back of my thigh. So I whip out my trusty phone camera to try to get a better view of it. Right as I get this gross thing in focus, the camera hits me with: "Switch to portrait mode?"
2
1
In my thesis defense on intuitive physics in neural networks, I had a shoutout to @dyamins on the "can perform task" blob here...it's obvious but many human modelling approaches bake so much into their models that they can't actually perform the task in any meaningful sense.
2
Yes! I'd love to see more work on representations learned on vision datasets vs. the biased and skewed images that children are exposed to (nice summary here from Linda Smith: frontiersin.org/articles/10.… )
1

















