#ANNs
LightNews LightNews
roostersworldja.bsky.social
A mushroom from Laughing Waters, St Anns, Jamaica.
February 17, 2026 at 3:31 AM
supurreme.etheirys.social
Welcome to the final days of jo-anns
May 23, 2025 at 10:23 PM
swinemiester.bsky.social
#photography #nature
Queen Ann's Lace
Queen Anns Lace photographed from below
December 7, 2024 at 6:23 PM
olivia.science
This hangs with the other statements in fig 1:

1️⃣ ANNs (artificial neural networks) are inspired by human organism

2️⃣ ANNs are a black box we don't understand

3️⃣ We understand neither ANNs nor cognition therefore they are similar

All 3 are misplaced! We unpack this...

doi.org/10.5281/zeno...
3/
Figure 1 in Guest, O., Nuñez Hernández, N. A., & Blokpoel, M. (2026). Understanding Artificial Neural Networks: Mysterianism about Known Mechanism is Mysticism. Zenodo. https://doi.org/10.5281/zenodo.20071869 As we shall see, three statements appear to hang together in disequilibrium, risking our reasoning, our metatheoretical calculus over our science, and eroding how well models can mediate between theory and observation (Elgin 2017; Guest 2023; Guest and Martin 2023; Morgan and Morrison 1999): Statement 1: ANNs are inspired by the human organism, typically the brain or cognition. Or worse: ANNs consti- tute a type of mind. (See 𝛼 in Figure 1.) While largely uncontroversial to claim this (e.g. Pickering 2014), it nonetheless requires extensive scientific under- standing of, and consensus on, human cognition, brain, and behaviour.3 We have nothing of the sort. Besides, if we did, and used these principles in engineering AI systems, then we would not have the problem of not understand- ing them. This is discussed in depth in Guest and Martin (2025b, 2023). Statement 2: ANNs constitute a black box that we do not mechanistically understand. Or worse: we cannot ever un- derstand ANNs because they are more intelligent than us. (See Appendix: ANNs models are a black box or unknowable even if opened and 𝛽 in Figure 1.) Given the ANNs are engineered systems, this is baseless marketing and misuse of terminology. This paper is dedi- cated to correcting and explaining this flawed assertion and its related reasoning errors. Statement 3: We understand neither human nor artificial cognition, and therefore they are similar. Or worse: we cannot ever understand either because both are equiva- lently hard. (See Appendix: We understand neither human nor artificial cognition, and therefore they are similar and 𝛼, 𝛽, and 𝛾 in Figure 1.) This is faulty reasoning (e.g. false analogy, argument from ignorance, discussed in Guest and Martin 2025b, 2023; “the equal opacity argument”, discussed in Peters 2023), as well as going against the previous two points
May 8, 2026 at 11:53 AM
lolgop.bsky.social
Martha-Anns are definitely the Delta variant of Karens.
May 29, 2024 at 11:20 AM
malizias.bsky.social
Anns the line up for season2/current season is done! We lost a gnome and got a hot drow instead #dnd #dndart #oc
November 30, 2024 at 1:44 PM
kordinglab.bsky.social
neuroAI comparisons of ANNs to brains do have a range of problems. Even more than I had realized. And I was worried before: www.biorxiv.org/content/10.1...
www.biorxiv.org
February 9, 2026 at 2:13 PM
shriekingdenizen.bsky.social
Anns at Sea!
September 21, 2026 at 1:32 AM
misheleneous.bsky.social
#BlueSkyArtShow #Narrow

With touches of yellow for #WeekYforYellow as seen in St Anns Place, Manchester - because you know I love a Ginnel 💛

#AlphabetChallenge #UrbanPhotography #StreetPhotography #DarkEntries #Manchester #Photography #Ginnel #EastCoastKin
St Anns Place ginnel in Manchester showing a metal fire escape and yellow painted wall and graffiti on disused shop units
June 21, 2025 at 10:40 AM
sevenkibibytes.bsky.social
a lot of anns
February 4, 2026 at 2:53 AM
darklinggaymer04.bsky.social
Anns skin looks really good.
#Fortnite #NintendoSwitch2
September 26, 2026 at 2:40 PM
karensussex.bsky.social
Prince Harry visits the community recording studio in St. Anns, Nottingham.
September 9, 2025 at 11:37 AM
Important work using ANNs to test computational implications of modularity.
bkhmsi.bsky.social Badr AlKhamissi @bkhmsi.bsky.social · Oct 20
🚀 Excited to share a major update to our “Mixture of Cognitive Reasoners” (MiCRo) paper!

We ask: What benefits can we unlock by designing language models whose inner structure mirrors the brain’s functional specialization?

More below 🧠👇
cognitive-reasoners.epfl.ch
October 20, 2025 at 1:26 PM
eghbal-hosseini.bsky.social
Why do diverse ANNs resemble brain representations? Check out our new paper with Colton Casto, @nogazs.bsky.social , Colin Conwell, Mark Richardson, & @evfedorenko.bsky.social on “Universality of representation in biological and artificial neural networks.” 🧠🤖
tinyurl.com/yckndmjt
Universality of representation in biological and artificial neural networks
Many artificial neural networks (ANNs) trained with ecologically plausible objectives on naturalistic data align with behavior and neural representations in biological systems. Here, we show that this...
tinyurl.com
December 27, 2024 at 8:14 PM
pauline001.bsky.social
bsky.app/profile/anns...
ann.sheshed.rocks Ann @ann.sheshed.rocks · Apr 10
Time is up! Something drastic must happen before he destroys the United States.

#SheShed
April 13, 2026 at 8:15 PM
prettypinkpansy.bsky.social
broke: girls, guys and theys
bespoke: daves, anns, and busters
cheapassgamer.com Cheap Ass Gamer @cheapassgamer.com · 16d
The First 200 People with the First or Last Name Dave, Davy, David, Ana, Ann, Anna, Anne, Annie and Buster at Each Store Before Noon Gets FREE Unlimited Game Play for the Day on SE‍PT. 12th via Dave & Buster's.

Games 1/2 Price All Day For Everyone That Day Too.
September 10, 2026 at 6:31 PM
shibbi.me
Fuck, this might actually be a path towards GOFAI and away from ANNs-do-everything

Yudkowsky you sickening bastard you’ve done it again
September 15, 2026 at 8:48 PM
beeezoniaaa.bsky.social
ALSO FINALLY GOT A CLEAR PICTURE OF ANNS ALL OUT ATTACK YESSSSS
June 28, 2025 at 6:07 PM
maitiuocoimin.bsky.social
Taigh-solais Rubh na h-Eist anns an Eilean Sgitheanach.
August 8, 2025 at 9:17 PM
dystopiabreaker.xyz
“gen AI” is largely just a product and marketing term. the technology is the same, enormous ANNs trained with supervised, unsupervised, RL, …, just pointed at different objectives
October 31, 2025 at 11:49 PM
tyrellturing.bsky.social
I think a major gap between ANNs and animals is the deeply impoverished stimuli that ANNs receive, which implies we should get better data for ANNs. But these folks had a diff idea: what if we instead impoverish the animals?

Better alignment with models!

journals.plos.org/ploscompbiol...

🧠📈 🧪
Parallel development of object recognition in newborn chicks and deep neural networks
Author summary Do machines learn like brains? The performance of all learning systems depends on both the learning machinery and experiences (training data) from which the system learns, so answering ...
journals.plos.org
January 3, 2025 at 7:46 PM
antlervel.vet
Anns and Nancys and Pats
February 13, 2025 at 12:43 AM
olivia.science
OK, let's talk about 3 important concepts:

ANNs, LLMs, & AI: "Definitions of AI and LLM are hard to pin down [&] ANN is an umbrella term for models"

Black box: Really not what people think because actually you can open it (read on in the PDF to find out) by design!

doi.org/10.5281/zeno...

5/
Box 1: Terminology for unpicking labels and conceptual pre- cursors to the reasoning behind ‘ANNs are a black box or un- knowable, even if opened’ depicted in Figure 1. ANNs, LLMs, & AI In modern parlance, in both scholarly and popu- lar science and technology discussions, these three acronyms are often used interchangeably. Defini- tions of AI and LLM are hard to pin down — as AI is a marketing term for making research sound flashy, neither ‘intelligence’ nor ‘artificial’ are coherent sci- entific concepts, and the ‘large’ in LLM is not used with any given cut-off (Guest 2026; Guest, Suarez, et al. 2025). ANN is an umbrella term for models of the data or of cognition that involve matrix multi- plications followed by squashing functions (Guest and Martin 2025b, 2023). Black Box A phrase from cybernetics, used inter alia in en- gineering and computer science, that denotes a system or sub-system that we (aim to) understand only through examining its input-output mappings (Ashby 1956; Glanville 2009). This pure functional- ist view on engineered systems does not preclude peeking inside for the ground truth after perform- ing the black box analysis. On the contrary, for non-engineered systems there is no peeking inside — such a manoeuvre is not possible — as no speci- fications or latent human-designed methods were used to create the system (Guest, Scharfenberg, et al. 2025). Leibniz’ Mill The Mill Argument, Leibniz’ Mill, or Leibniz’ Gap, is an argument against the idea that mechanical components suffice to understand cognition. Leib- niz (1714/1989) asks us to imagine stepping inside a machine that produces cognition in the same way we can a mill, an exemplary machine. In so do- ing we observe the interactions of the mill’s cog- wheels, levers, and other components. By look- ing at the mechanical constituents of the machine, Leibniz explains, there will never be anything we will come across that explains cognition (Cummins 2000, 2010; Duncan 2012; Hattab 2011; Kulstad…
May 9, 2026 at 2:39 PM
highlander-sheila.bsky.social
Aodach-fo an-còmhnaidh agus anns a h-uile àite - Underwear—always and everywhere.
July 22, 2026 at 9:12 PM
timothyoleary.bsky.social
This is why banging on about the power of simplistic models is problematic. It kills curiosity. We don't need to bang on about the power of ANNs, because they are now unavoidable parts of everyday life. By all means we need to teach ANNs, but our job as educators and scientists is to go deeper!
December 17, 2024 at 2:14 PM