34 stories tagged neural-networks, newest first.
4 points by falperc | 1 comments
GitHub repo for Doomformer, which computes neural networks including transformers using DOOM game mechanics like voodoo dolls, conveyor belts, lava and doors, verified bit-exact.
30 points by chenglou | 11 comments
Project page for Handwired, a tool that compiles ordinary JavaScript code into exact, differentiable neural networks runnable in the browser, with demos like a mini OS.
602 points by speckx | 133 comments
Blog post by Alex Wang explaining transformer layers (MLPs, gated MLPs, self-attention) as associative memory stores, with code and an interactive app.
4 points by vismit2000 | 1 comments
Landing page for Handwired, a tool that compiles regular JavaScript code into an exact, differentiable neural network runnable in a browser without training or GPU.
768 points by themgt | 300 comments
An informal research essay by Nick Cammarata at Goodfire arguing polysemanticity stems from fixable issues, not superposition, making neurons interpretable at scale.
252 points by sbulaev | 118 comments
An arXiv paper showing AI models can embed encrypted neural network backdoors that provably hide arbitrary capabilities from elicitation-based safety evaluations.
84 points by jbaudanza | 16 comments
Blog post announcing a publicly available neural network that generates Korean Hangul handwriting pen strokes, released for Hangul Day with a browser demo.
269 points by E-Reverance | 79 comments
Research page from QLabs presenting Dust, a method for pretraining transformer models without backpropagation, with authors, code link, and architecture diagram.
273 points by PaulHoule | 138 comments
Ars Technica article on an AI that beat top Stratego players by adding a second neural network to guess the identity of hidden pieces.
33 points by costco | 2 comments
A blog post by Eli Bendersky explaining the softmax function mathematically and deriving its derivative for machine learning use.
336 points by sans_souse | 25 comments
AI by Hand is a site teaching AI and deep learning concepts through hand-worked math exercises; the captured page was blank.
1427 points by MaxLeiter | 633 comments
A short fiction blog post parodying Terry Bisson's "They're Made Out of Meat," with characters marveling that language models are made only of weights.
834 points by 0xkato | 228 comments
A blog post giving a math-light walkthrough of how transformer-based large language models work internally.
320 points by jamie-simon | 142 comments
An arXiv position paper arguing that a scientific theory of deep learning is emerging, surveying five strands of research such as solvable models, scaling limits, and universal behaviors.
372 points by 0bytematt | 25 comments
A visual, beginner-friendly tutorial introducing PyTorch, covering tensors, autograd, and building a simple neural network.
693 points by suioir | 63 comments
Andrej Karpathy's free video course page on building neural networks from scratch in Python, from backpropagation (micrograd) up to GPT-style language models.
468 points by auraham | 85 comments
Jay Alammar's illustrated blog post explaining the Transformer neural network architecture and its self-attention mechanism with visual diagrams.
478 points by dvrp | 100 comments
Project page for Apple's SHARP, a method that regresses a 3D Gaussian representation from a single photo in under a second for photorealistic novel view synthesis.
335 points by swatson741 | 132 comments
Andrej Karpathy's 2016 Medium essay arguing that practitioners should understand backpropagation because it is a leaky abstraction.
357 points by amazonhut | 170 comments
GitHub repository for RustGPT, a transformer-based large language model written entirely in Rust from scratch.
473 points by theahura | 176 comments
A Substack essay from 12 Grams of Carbon arguing that deep learning is applied topology, explaining how neural networks transform data lying on manifolds.
430 points by eyvindn | 84 comments
Google Research article presenting Differentiable Logic Cellular Automata, which learn local logic-circuit rules to reproduce Game of Life and generate target patterns.
331 points by georgehill | 90 comments
Blog post by Isaac Liao and Albert Gu describing a method that solves ARC-AGI puzzles using lossless information compression without pretraining.
461 points by jnord | 854 comments
BCS opinion article by Professor Eerke Boiten arguing that current AI systems are unsuitable for serious applications and may represent a dead end.
![Screenshot of nobelprize.org: Nobel Prize in Physics awarded to John Hopfield and Geoffrey Hinton [pdf]](https://hn.urlbox.com/shots/renders/2024/10/8/839f80f0-8c22-4cc5-9aad-2bcf0091ab29.jpg)
905 points by drpossum | 754 comments
Nobel Prize scientific background document on the 2024 Physics prize awarded to John Hopfield and Geoffrey Hinton for foundational work on artificial neural networks.
![Screenshot of youtube.com: But what is a GPT? Visual intro to Transformers [video]](https://hn.urlbox.com/shots/renders/2024/4/2/71716e98-88ef-4714-9527-00dfc652e546.jpg)
387 points by huhhuh | 46 comments
A 3Blue1Brown YouTube video giving a visual introduction to GPT and the transformer architecture, chapter 5 of its deep learning series.
408 points by LaserPineapple | 94 comments
A hackerllama blog post walking through an end-to-end worked example of transformer math using small random vectors and matrices.
412 points by Anon84 | 132 comments
arXiv listing for a book by Jentzen, Kuckuck, and von Wurstemberger giving a mathematically rigorous introduction to deep learning methods, implementations, and theory.
642 points by qwertyforce | 55 comments
Animated AI is a site of 3D animations and instructional videos explaining neural network concepts, starting with the basic convolution algorithm.
395 points by 1wheel | 176 comments
Google PAIR interactive explorable from August 2023 explaining grokking, where models suddenly shift from memorizing training data to generalizing.
515 points by Sai_ | 196 comments
Ask HN thread requesting a simple explanation of transformer models and the "Attention Is All You Need" paper, with community replies and resource links.
420 points by dataminer | 29 comments
A PDF of François Fleuret's The Little Book of Deep Learning, a short introductory textbook on deep learning.
594 points by jasim | 46 comments
A long-form tutorial explaining how transformer neural networks work from the ground up, covering matrix multiplication, attention, and backpropagation.
546 points by whereistimbo | 64 comments
Course page for Andrej Karpathy's Neural Networks: Zero to Hero, a video series building neural networks from scratch in code up to GPT-style language models.