[HN Gopher] The physical process that powers a new type of gener...
___________________________________________________________________
The physical process that powers a new type of generative AI
Author : digital55
Score : 79 points
Date : 2023-09-19 14:50 UTC (8 hours ago)
(HTM) web link (www.quantamagazine.org)
(TXT) w3m dump (www.quantamagazine.org)
| Animats wrote:
| OK, so switching to 1/x^2 diffusion, instead of heat-type
| diffusion, has some advantages. Interesting. Lots of other
| functions to try. Look at the history of activation functions.
| Sigmoids, ramps, thresholds.
| jcims wrote:
| Does using a physical process as the model by which the network
| learns and infers create an opportunity to implement the network
| physically? In this case it seems like it could be an interesting
| way to build things like modulators and demodulators, amplifiers,
| noise filters, etc.
| sroussey wrote:
| https://arxiv.org/abs/2302.04265
| zackmorris wrote:
| This reminds me of Boltzmann Machines:
|
| https://www.mygreatlearning.com/blog/understanding-boltzmann...
|
| https://medium.com/@neuralnets/boltzmann-machines-transforma...
|
| I'm having trouble finding a good introduction, but if I remember
| correctly, BMs started with the premise that nerves that fire
| together wire together. It can be easier to visualize that
| process than to think about gradient descent.
|
| Since all NNs can be reduced to a matrix taking an input vector
| and returning an output vector, I think we often get lost in the
| weeds arguing about the merits of various types. IMHO it's more
| useful to compare different classes of machine learning instead.
|
| Honestly LLMs have strayed so far from what I thought was going
| to happen back in the late 90s that I'm still not sure how I feel
| about all of this. I think that our brains evolved more like an
| ant colony or mycelium in a forest, where countless small
| individuals form ever-more complex networks through mutual aid
| and evolution. What we think of as consciousness is already
| present in everything and the network happens to reach a level of
| complexity high enough for that source to interact with our 3D
| universe (like a radio antenna). Computing clusters could have
| achieved that decades ago but we went with SIMD video cards that
| can only run one algorithm per agent, not MIMD which could evolve
| each agent individually and run say 100 billion agents
| simultaneously like the neurons in our brain.
|
| And the fact that AI is going in a SAAS/subscription direction
| really concerns me. I don't know if there's time now to try these
| other algorithms before 1 or 2 companies dominate the industry
| under some kind of New World Order. Maybe it's just me though
| hah.
| wormius wrote:
| I can picture a PKD novel about God being a subscription based
| AI, perhaps "salvation" requires monthly "tithing" or else you
| get cut off from everlasting life (or the real grease under the
| hood : social connections/power). Perhaps you could subscribe
| to various differing AI gods... hedge your bets as it were
| through a costly polytheism. Perhaps the social power by those
| who donate the most... Almost like a Scientology type religion,
| where those who buy in get more compute power to enact their
| goals.
|
| Apologies for the derail.
| phero_cnstrcts wrote:
| As WEF states it: Every product is a service waiting to happen.
| nico wrote:
| Has anyone used any of the generative models mentioned in the
| article? Didn't see any images or direct comparisons of the
| outputs with current diffusion models
| GaggiX wrote:
| https://arxiv.org/abs/2302.04265 You can see some results in
| the paper.
| dr_dshiv wrote:
| That's beautiful.
|
| Wishful thinking that quantum computing will find some kind of
| application in this...
| Der_Einzige wrote:
| Unfortunately, unlike in NLP where swapping out decoding
| techniques frequently leads to far better generation (i.e.
| novelty sampling like top-p/top-k for text gen, beam search for
| seq-seq tasks), this is not necessarily the case for diffusion
| based image generators.
|
| Despite many methods being mathematically "superior" to
| traditional euler adaptive, it remains the default settings for a
| reason in all the major UIs (Automatic1111, Comfy). I have a lot
| of fun playing with other samplers, especially ones which
| converge and thus allow large sampling steps, but the impact is
| not as massive here as it is in NLP and we may be over thinking
| this side of the pipeline and not thinking enough about other
| important things (i.e. mixing in other losses besides regular
| diffusion loss for more control similar to controlnet).
___________________________________________________________________
(page generated 2023-09-19 23:01 UTC)