Not advanced maths per se; neural networks are amazing! Fuzzy matching based on experience - taken to an incredible level. And, tuneable by internal simulation (imagination).
this post was submitted on 15 Nov 2024
1254 points (99.5% liked)
Science Memes
11130 readers
2941 users here now
Welcome to c/science_memes @ Mander.xyz!
A place for majestic STEMLORD peacocking, as well as memes about the realities of working in a lab.
Rules
- Don't throw mud. Behave like an intellectual and remember the human.
- Keep it rooted (on topic).
- No spam.
- Infographics welcome, get schooled.
This is a science community. We use the Dawkins definition of meme.
Research Committee
Other Mander Communities
Science and Research
Biology and Life Sciences
- !abiogenesis@mander.xyz
- !animal-behavior@mander.xyz
- !anthropology@mander.xyz
- !arachnology@mander.xyz
- !balconygardening@slrpnk.net
- !biodiversity@mander.xyz
- !biology@mander.xyz
- !biophysics@mander.xyz
- !botany@mander.xyz
- !ecology@mander.xyz
- !entomology@mander.xyz
- !fermentation@mander.xyz
- !herpetology@mander.xyz
- !houseplants@mander.xyz
- !medicine@mander.xyz
- !microscopy@mander.xyz
- !mycology@mander.xyz
- !nudibranchs@mander.xyz
- !nutrition@mander.xyz
- !palaeoecology@mander.xyz
- !palaeontology@mander.xyz
- !photosynthesis@mander.xyz
- !plantid@mander.xyz
- !plants@mander.xyz
- !reptiles and amphibians@mander.xyz
Physical Sciences
- !astronomy@mander.xyz
- !chemistry@mander.xyz
- !earthscience@mander.xyz
- !geography@mander.xyz
- !geospatial@mander.xyz
- !nuclear@mander.xyz
- !physics@mander.xyz
- !quantum-computing@mander.xyz
- !spectroscopy@mander.xyz
Humanities and Social Sciences
Practical and Applied Sciences
- !exercise-and sports-science@mander.xyz
- !gardening@mander.xyz
- !self sufficiency@mander.xyz
- !soilscience@slrpnk.net
- !terrariums@mander.xyz
- !timelapse@mander.xyz
Memes
Miscellaneous
founded 2 years ago
MODERATORS
Don't be fooled to think computer neural networks is how the brain is structured. Through out history we've always compared the brain to the most advanced technology at the time. From clocks, to computers with short and long term memory, and now to neural networks.
That is a good point, though the architecture of computer neutral networks is inspired by how we think the brain works, and if I understand correctly there is some definite similarity in the architecture.
Lots of difference though, still!
I would guess that every statement made is kind of true. It is a clock, a computer and a LLM,...
I would even go as far as LLM is the closest to a functioning brain we can produce from a functional perspective. And even the artificial brains are to complex to understand in detail.
I reckon we can get a lot closer than an LLM in time. For one thing, the mind has particular understanding of interim steps whereas, as I understand it, the LLM has no real concept of meaning between the inputs and the output. Some of this interim is, I think, an important part of how we assess truthfulness of generated ideas before we put them into words.
load more comments
(3 replies)
load more comments
(1 replies)
The second thing about microslippage is why I, even though I would say I'm transhumanist, would only ever go full cyborg if the robot parts had a sense of touch.
I don't wanna pet my dog and not only not feel their fur, but also end up crushing them with my super strength.
i feel like being objectively better than your body is a pretty fundamental requirement for transhumanism, like generally what's shown as the ideal transhumanist body is a nanomachine swarm that can just make precisely whatever you want at any moment, you can be ostensibly human one moment and then turn into a fucking jet plane and go to the other side of the world and become human again to traipse through the jungles.
Also masturbation might be a challenge in that scenario.
Also the ability of mirror neurons to watch someone do a thing, then conceptualize and execute it with your body is extremely interesting.
I've seen some pretty awesome prosthetics that are controlled the same way you would use your limbs before they were lost by connecting to nerves; but they still don't feel anything. At least, not in the sense that the appendage itself is sending signals to your brain for it. There is still phantom sense/pain. You can get a false sense of touch in VR, too.
load more comments
(6 replies)
I always imagine it more like neural networks. simply based on a lot of training and experience. As an example think of times when you step onto a non moving escalator. Your mind definitely knows its not moving but you still can't defeat the trained expectation of jerk.
My brain is like a neural network? No way...
more like neural networks are maybe like your brain? dunno not an expert, just a feeling
neural networks are like how small parts of your brain look like they work
Layered as well. Little bits process very specific things and simplify it for the beast.
Take shrooms and watch as the divisions between the little bits break down into absolute chaos :D
load more comments
(1 replies)
load more comments
(2 replies)
A lot of it is less math and more just approximations using old data, just fitting a complex statistical model neural nets suck ass at math
Yeah, your brain is not doing projectile motion equations in real time, it's the same process as teaching a neutral network to approximate a parabola.
Don't get me wrong, it's incredibly impressive that this prediction in our brain requires the visual processing of data from eyes to identify an object flying through the air, moving our hand in a perfect intercept course to catch it. All without having to have a ton of data points to 'train' on.
load more comments
(1 replies)
I always thought about how interesting it is that handing things to people is so reliable. We just kind of know exactly when the other person has grabbed something enough for us to let go.
And then there's the rare moment when you think they have it so you let go and it falls to the floor 😭
Most people who've been juggling for awhile don't need too much additional practice to be able to do at least a few blindfolded catches just because of how consistent your throws get after awhile.
The other thing that's interesting is how pattern recognition in flying things people aren't generally used to seeing develops. I used to play ultimate, and when people start learning how a frisbee flies they might be susceptible to chasing it down by following along the path of the disc rather than moving directly to where it's going to end up. This is sometimes called dogging the disc because (many) dogs do the same thing. But then you learn to "read" the disc and you can tell by the flight path and angle of the disc where it's going to land.
view more: next ›