67
submitted 7 months ago by flashgnash@lemm.ee to c/asklemmy@lemmy.ml

There's a video on YouTube where someone has managed to train a network of rat neurons to play doom, the way they did it seems reminiscent of how we train ML models

I am under the impression from the video that real neurons are a lot better at learning than simulated ones (and much less power demanding)

Could any ML problems, such as natural language generation be solved using neurons instead and would that be in any way practical?

Ethically at this point is this neuron array considered conscious in any way?

you are viewing a single comment's thread
view the rest of the comments
[-] aDogCalledSpot@lemmy.zip 3 points 7 months ago

Our current ML Neural Networks work (simplified) like this: A neuron emits a number and the next neuron calculates a new number to emit based on all the values given to it by other neurons as inputs. Our brain can't fire numbers in this way. So there's a fundamental difference. Bridging this difference to create NNs that are more similar to our brains is the basis of the study of Spiking Neural Networks. Their performance so far isn't great, but it's an interesting topic of research.

this post was submitted on 08 Apr 2024
67 points (92.4% liked)

Asklemmy

43822 readers
876 users here now

A loosely moderated place to ask open-ended questions

Search asklemmy ๐Ÿ”

If your post meets the following criteria, it's welcome here!

  1. Open-ended question
  2. Not offensive: at this point, we do not have the bandwidth to moderate overtly political discussions. Assume best intent and be excellent to each other.
  3. Not regarding using or support for Lemmy: context, see the list of support communities and tools for finding communities below
  4. Not ad nauseam inducing: please make sure it is a question that would be new to most members
  5. An actual topic of discussion

Looking for support?

Looking for a community?

~Icon~ ~by~ ~@Double_A@discuss.tchncs.de~

founded 5 years ago
MODERATORS