#neuralnets — Public Fediverse posts

Neural networks train by constructing a computational graph in the forward pass, chaining basic operations such as x × y × z into composite functions of the inputs.

Derivatives of the output with respect to every input are then obtained in the backward pass by applying the chain rule at each node, where local gradients multiply: ∂f/∂y = ∂f/∂(x × y) × ∂(x × y)/∂y and ∇ₓz = ∇ₓy · ∇ᵧz, with intermediate values stored along the graph.

This process updates the parameters of convolutional networks that classify medical scans to flag early-stage tumors in hospital imaging systems.

#NeuralNetworks #NeuralNets #DL #ML #DeepLearning #MachineLearning #AI #NNs #CNN

#HPsCommentary

👉#LLMsAreIntelligent!👈

(11/n)

... much of what we consider #Intelligence is inherently dialogic, hence social; it requires a theory of mind👈. Since the interior state of another being can only be understood through interaction, 👉no objective answer is possible to the question of when an “it” becomes a “who”👈 — but 👉for many people, #NeuralNets running on computers are likely to cross this threshold in the very near future.👈"

As...

@mina @si_irini @appassionato

Tau leptons are electrons but heavier, but unlike electrons they are unstable and create many different detector signatures. So, #machinelearning This #CMSpaper describes how we use convolutional #neuralnets (that's ones that do image recognition!) to better see tau leptons arxiv.org/abs/2511.05468

Tau leptons are electrons but heavier, but unlike electrons they are unstable and create many different detector signatures. So, #machinelearning This #CMSpaper describes how we use convolutional #neuralnets (that's ones that do image recognition!) to better see tau leptons arxiv.org/abs/2511.05468

Tau leptons are electrons but heavier, but unlike electrons they are unstable and create many different detector signatures. So, #machinelearning This #CMSpaper describes how we use convolutional #neuralnets (that's ones that do image recognition!) to better see tau leptons arxiv.org/abs/2511.05468

🧠 Human-like Working Memory from Artificial Intrinsic Plasticity Neurons

https://arxiv.org/abs/2512.15829

#ai #llm #research #cs #arxiv #neuralnets #memory

🤯 stable-pretraining-v1: Foundation Model Research Made Simple

https://arxiv.org/abs/2511.19484

#ai #llm #neuralnets #training #software #research #cs #foundationmodels

📡 'Mind-captioning' technique can read human thoughts from brain scans

https://medicalxpress.com/news/2025-11-mind-captioning-technique-human-thoughts.html

#brain #neuroscience #neuralnets #mind #thoughts #telepathy

⚡ Team develops high-speed, ultra-low-power superconductive neuron device

https://techxplore.com/news/2025-10-team-high-ultra-power-superconductive.html

#electronics #neuralnets #hardware #superconductivity #engineering #research

THIS IS AN IMPORTANT ADVANCE IN OUR UNDERSTANDING OF COMPLEX SYSTEMS.

https://www.sciencedirect.com/science/article/pii/S0303264725002187?via%3Dihub

h/t @bruces

#NeuralNets #ComplexityScience #thermodynamics

Paired Neural Network for Matching Experimental and Predicted Infrared Spectra.
Anal. Chem. 2025
https://doi.org/10.1021/acs.analchem.5c01607
#infrared #neuralnets
Follow us on Bluesky: https://bsky.app/profile/clirspec.org

Ah yes, the groundbreaking revelation that AI models can be squished into datasets 🤯. Now we can store these majestic neural nets in our back pockets, because who wouldn't want to lug around gigabytes of "innovation"? 📦🎉
https://www.scalarlm.com/blog/llm-deflate-extracting-llms-into-datasets/ #AIinnovation #AIstorage #neuralnets #techrevolution #dataengineering #HackerNews #ngated

🤖🆚📱 In this battle of neural nets versus cellular automata, prepare for a mind-numbing descent into a sea of #numbers that even a calculator wouldn't bother reading. 😂 Who knew that updating cells ON and OFF could reach levels of #complexity typically reserved for assembling IKEA furniture? 📊🔧
https://www.nets-vs-automata.net/ #neuralnets #cellularautomata #techhumor #IKEAassembly #HackerNews #ngated

Neural Nets vs. Cellular Automata

https://www.nets-vs-automata.net/

#HackerNews #NeuralNets #CellularAutomata #MachineLearning #AI #Research #TechTrends

I just discovered the ARC-AGI initiative and the associated test to estimate how close "AI" models are from #AGI

https://arcprize.org/arc-agi

While I found the initiative interesting, I'm not sure I understand what in this test really guarantees that the model is capable of some form of generalization and problem-solving.
Wouldn't it be possible for specialized pattern-matching/discovering algorithms to solve such problems?
I imagine some computer scientists, mathematicians or computational neuroscientists have already had a look at this, so would anyone knows of some articles/blogs on the topic?

Maybe @wim_v12e? Is this something you already looked at?

#AI #machineLearning #neuroscience #cognition #computationalNeuroscience #neuralNets #lazyWeb

Hill Space: Neural nets that do perfect arithmetic (to 10⁻¹⁶ precision)

https://hillspace.justindujardin.com/

#HackerNews #HillSpace #NeuralNets #Arithmetic #Precision #Technology #10^-16

GLASSR-Net: Glass Substrate Spectral Restoration Neural Network for Fourier Transform Infrared Microspectroscopy in the Fingerprint Region.
Anal. Chem. 2025
https://doi.org/10.1021/acs.analchem.4c06805
#infrared #neuralnets

This video will change your mind about Neural Networks - by Daniel Boctor

via Invidious:
https://inv.nadeko.net/watch?v=eCU2vQs0Q6s
(or YT: https://www.youtube.com/watch?v=eCU2vQs0Q6s)

Brilliant explainer video with great visualizations on how neural networks work.

#NeuralNetworks #NeuralNets #AI #ArtificialIntelligence #Video #Statistics

@kellogh It's an advanced pattern recognition machine, nothing more.

And yes, we don't really know what's happening within #LLMs #NeuralNets - and this makes it worse!

AIs are intuitive, not thinking machines, which is not enough to produce code that is high quality and can be trusted:

Very interesting thread:
https://floss.social/@janriemer/109479731267566070

Also, there is _so much more_:
- I want an #AI, that _expresses uncertainty_ with line number range
- asks questions back, not just spit out bs!

@laund

Remember last week's #nobel2024 #nobelprize in physics ?
I fondly remember my student days and the course on #NeuralNets in summer 1994 given by Helge Ritter
from #unibielefeld, where I learned about the #Hopfield model for the first time.
I was able to dig out my 30 year old lecture notes, including the citation of the seminal 1984 PNAS paper, see below. Neural Networks have come a long was since then ! Yours, Steffen

Wait, #LLMs or #NeuralNets can't reason!? This is so surprising! How could that happen!? This is unbelievable! I'm in shock!

But they surely have feelings, right...right!?

#AI #ArtificialIntelligence #LLM #NeuralNetworks

Deep learning folk should ban themselves from using the word "model" for a neural net! It makes scientific discussions really hard. Ecologist: "what is it a model of?" Physicist: "what is it a model of?" Empirical scientist: "Can I use this model in my model? What's our model of this model?"
.... Anyway: "network" is overloaded too, but as least "neural net" is pretty unambiguous (tho, I think, unfashionable). Let's neural net ("NN"). #deeplearning #terminology #academia #neuralnets

Does anyone know the URL for the "observatory" website (I think that's what they called it) where one of the AI/DNN labs had analysed various machine vision models and built a map of all of the nodes.

You could click on each node and see the images (and sometimes text) that triggered it, and also images that were generated when they excited that node while clamping others (like Deep Dreams)

I can't remember who it was and can't find it.

#AI #DeepNeuralNetworks #NeuralNets #YOLO #deepdream

The Artificial Intelligence Papers

Original Research Papers With Tutorial Commentaries

https://jamesstone.sites.sheffield.ac.uk/books/theaipapers

Friend and colleague Jim Stone has a new book, with a "no mercy" cover and bomber content for understanding the technical foundations of the current AI moment

#AI #generativeAI #NeuralNets

My seventh Math Research Livestream is now available on YouTube:

https://youtu.be/gKm-5vkb4yc

In this one I decided to pick up with where I ended the previous week, writing code for my discrete neural nets paper (https://arxiv.org/abs/2308.00677). This time I did actually get a decent amount of code written!

#math #livestream #Twitch #algebra #AbstractAlgebra #AI #MachineLearning #NeuralNets #combinatorics #UniversalAlgebra #CategoryTheory

My next Math Research Livestream starts in about 30 minutes on Twitch! Check it out at https://www.twitch.tv/charlotteaten. I decided to pick up with where I ended last week, writing code for my discrete neural nets paper (https://arxiv.org/abs/2308.00677).

#math #livestream #Twitch #algebra #AbstractAlgebra #AI #MachineLearning #NeuralNets #combinatorics #UniversalAlgebra #CategoryTheory