Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

we trained a fruit fly to understand emotion We created a neural network from the male drosophila connectome, then trained it on human emotions. It was shocking to see how good it was at identification (better than some humans I know)

Nathan Roll

1,310 subscribers

611,753 Aufrufe • vor 22 Tagen •via X (Twitter)

Wissenschaft & Technologie Bildung

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

Is it possible to adapt a neural network on the fly at the test time to cope with distribution shifts? RNA does precisely that by creating a closed-loop feedback system. We will present it on Wed afternoon at #ICCV2025. 1/n

Is it possible to adapt a neural network on the fly at the test time to cope with distribution shifts? RNA does precisely that by creating a closed-loop feedback system. We will present it on Wed afternoon at #ICCV2025. 1/n

Amir Zamir

21,719 Aufrufe • vor 3 Jahren

LLMs are built out of neural networks, so it was easy to extend to the fruit fly connectome The first brain ever uploaded to a blockchain. Every neuron fire running as standard Solana transactions on Fogo As long as the wallet's funded, this guy has digital immortality

LLMs are built out of neural networks, so it was easy to extend to the fruit fly connectome The first brain ever uploaded to a blockchain. Every neuron fire running as standard Solana transactions on Fogo As long as the wallet's funded, this guy has digital immortality

Doug Colkitt

53,810 Aufrufe • vor 9 Tagen

1/ we trained a behavior cloning policy on 40 demos of picking and placing a plush toy. the result is so smooth that you would think it was teleoperated. it's also badly overfit. to explore how well it generalizes, we probed it along four axes to find where it suffers most.

1/ we trained a behavior cloning policy on 40 demos of picking and placing a plush toy. the result is so smooth that you would think it was teleoperated. it's also badly overfit. to explore how well it generalizes, we probed it along four axes to find where it suffers most.

Lucy Cai

26,270 Aufrufe • vor 1 Monat

Lorraine Kelly, "I saw a video from Suella Braverman on TikTok and I honestly thought it was AI.. Because it was so ridiculous.. You know it was so silly." Lorraine expressing how we all felt when we saw it 😅

Lorraine Kelly, "I saw a video from Suella Braverman on TikTok and I honestly thought it was AI.. Because it was so ridiculous.. You know it was so silly." Lorraine expressing how we all felt when we saw it 😅

Farrukh

292,996 Aufrufe • vor 2 Jahren

This afternoon we left the puppy at home with uncle Jason and we went out with Detective Dug 🇨🇦. There were some dogs not on leashes (apparently the big signs pointing to the off leash area 0.8km away was too hard for their humans to understand) so I stood still on the path and had them focus on me so Dug could take his human and hide out of sight. He can get scared by strange dogs. The one dog's human kept calling him and it took forever for him to go. Maybe the human was as bad at speaking dog as they were at reading signs in human language? Then Dug and I played scent games. I've never done that away from home. It's way harder to choose which cone has the scent under it when there's strange humans and animals around. We're gonna have to really practice that! We also got to see geese and a rabbit! We stopped at the mailbox and I carried the mail home!!! It was the bestest day! Maybe almost as good as tomorrow is going to be!!!

This afternoon we left the puppy at home with uncle Jason and we went out with Detective Dug 🇨🇦. There were some dogs not on leashes (apparently the big signs pointing to the off leash area 0.8km away was too hard for their humans to understand) so I stood still on the path and had them focus on me so Dug could take his human and hide out of sight. He can get scared by strange dogs. The one dog's human kept calling him and it took forever for him to go. Maybe the human was as bad at speaking dog as they were at reading signs in human language? Then Dug and I played scent games. I've never done that away from home. It's way harder to choose which cone has the scent under it when there's strange humans and animals around. We're gonna have to really practice that! We also got to see geese and a rabbit! We stopped at the mailbox and I carried the mail home!!! It was the bestest day! Maybe almost as good as tomorrow is going to be!!!

Team Servicerottie🇨🇦🐕‍🦺🦽

18,147 Aufrufe • vor 1 Jahr

🚨| Gigi Hadid opened #VSFashionShow2024 by referencing Taylor Swift! "There's an aspect to it that I was trained to do by Taylor on her tour. She was like, 'I'm going to show you how we do this.' And now I'm using it tonight."

🚨| Gigi Hadid opened #VSFashionShow2024 by referencing Taylor Swift! "There's an aspect to it that I was trained to do by Taylor on her tour. She was like, 'I'm going to show you how we do this.' And now I'm using it tonight."

The Swift Society

1,956,386 Aufrufe • vor 1 Jahr

i minted my first nft collection as a full-time artist. the work is built from a hopfield network, one of the most fundamental forms of neural network. it learns different writing systems, then begins to forget them. as its memories decay, it starts producing glyphs it was never taught.

i minted my first nft collection as a full-time artist. the work is built from a hopfield network, one of the most fundamental forms of neural network. it learns different writing systems, then begins to forget them. as its memories decay, it starts producing glyphs it was never taught.

Kat ⊷ the Poet Engineer

92,087 Aufrufe • vor 3 Monaten

After years using autopilot, I was able to see Tesla Full Self-Driving (Supervised) in action on city streets in Rome. As a passenger I was astonished by the driving smoothness, and how it handled traffic, roundabouts, pedestrians and works on the street, better than most humans.

After years using autopilot, I was able to see Tesla Full Self-Driving (Supervised) in action on city streets in Rome. As a passenger I was astonished by the driving smoothness, and how it handled traffic, roundabouts, pedestrians and works on the street, better than most humans.

Franco Mossotto

57,435 Aufrufe • vor 7 Monaten

"We can rebuild him. We have the technology. We can make him better than he was. Better, stronger, faster" Well.... maybe not. Still, it would be good to see him in that uniform again. #NYGiants

"We can rebuild him. We have the technology. We can make him better than he was. Better, stronger, faster" Well.... maybe not. Still, it would be good to see him in that uniform again. #NYGiants

BaddogSports

93,119 Aufrufe • vor 5 Monaten

Anne Hathaway revealed she trained with a professional mime for two weeks to prepare for Ella Enchanted (2004). "I worked with a mime for about two weeks. I had to learn how to control my body and make it look like someone else was controlling me." "It was hysterical. He was trying to get me to do the classic pratfalls, and I was like, 'I'm not interested in being a mime. I don't see my future in miming.'" "So we stuck to the script."

Anne Hathaway revealed she trained with a professional mime for two weeks to prepare for Ella Enchanted (2004). "I worked with a mime for about two weeks. I had to learn how to control my body and make it look like someone else was controlling me." "It was hysterical. He was trying to get me to do the classic pratfalls, and I was like, 'I'm not interested in being a mime. I don't see my future in miming.'" "So we stuck to the script."

Movies Scenes 🎫

100,653 Aufrufe • vor 2 Monaten

How can we leverage diverse human videos to improve robot manipulation? Excited to introduce EgoVLA — a Vision-Language-Action model trained on egocentric human videos by explicitly modeling wrist & hand motion. We build a shared action space between humans and robots, enabling seamless transfer. With some robot demos, EgoVLA becomes a powerful, generalizable robot policy.

How can we leverage diverse human videos to improve robot manipulation? Excited to introduce EgoVLA — a Vision-Language-Action model trained on egocentric human videos by explicitly modeling wrist & hand motion. We build a shared action space between humans and robots, enabling seamless transfer. With some robot demos, EgoVLA becomes a powerful, generalizable robot policy.

Ruihan Yang

58,891 Aufrufe • vor 1 Jahr

The sdxl-VAE models a substantial amount of noise. Things we can't even see. It meticulously encodes the noise, uses precious bottleneck capacity to store it, then faithfully reconstructs it in the decoder. I grabbed what I thought was a simple black vector circle on a white background but the VAE latched on to a veritable Navajo quilt of background noise. I was absolutely flummoxed until I realized what was going on! A lot of capacity being used on things we don't need to be modelling at all. Suspected culprit is group norm.

The sdxl-VAE models a substantial amount of noise. Things we can't even see. It meticulously encodes the noise, uses precious bottleneck capacity to store it, then faithfully reconstructs it in the decoder. I grabbed what I thought was a simple black vector circle on a white background but the VAE latched on to a veritable Navajo quilt of background noise. I was absolutely flummoxed until I realized what was going on! A lot of capacity being used on things we don't need to be modelling at all. Suspected culprit is group norm.

Rudy Gilman

52,110 Aufrufe • vor 1 Jahr

I love how we actually got to see how fast it was… Trunks was NOT playing 😭🔥

I love how we actually got to see how fast it was… Trunks was NOT playing 😭🔥

Gaming NextDoor

1,282,642 Aufrufe • vor 7 Monaten

LLMs, trained only on text, might already know more about other modalities than we realized; we just need to find ways elicit it. project page: w/ Phillip Isola and Brian Cheung

LLMs, trained only on text, might already know more about other modalities than we realized; we just need to find ways elicit it. project page: w/ Phillip Isola and Brian Cheung

Sophie Wang

92,213 Aufrufe • vor 11 Monaten

The Bunsen, Beaker, Bernoulli & Brix humans brought Bernoulli to come visit me. They also brought snacks! It was great! We played in the yard and had sniffs and nuzzles and even held paws. It was great. But we really need to find a way to ditch the human chaperones at some point. 😉 #DogLove #Chesnoulli Video description for inclusivity: Chesnyy sitting on the couch with Bernoulli on the floor in front of her. He looks up at her and they nuzzle each other. He attempts to sniff her a bit more in depth and the humans break it up.

The Bunsen, Beaker, Bernoulli & Brix humans brought Bernoulli to come visit me. They also brought snacks! It was great! We played in the yard and had sniffs and nuzzles and even held paws. It was great. But we really need to find a way to ditch the human chaperones at some point. 😉 #DogLove #Chesnoulli Video description for inclusivity: Chesnyy sitting on the couch with Bernoulli on the floor in front of her. He looks up at her and they nuzzle each other. He attempts to sniff her a bit more in depth and the humans break it up.

Team Servicerottie🇨🇦🐕‍🦺🦽

23,077 Aufrufe • vor 1 Jahr