AI & machine learning2017 · shared on Hacker News

Deep Neural Networks – Attention is all you need (No recurrence or convolutions)

Explore Deep Neural Networks – Attention is all you need (No recurrence or convolutions), its original source and Hacker News discussions. Discover community perspectives and save it to your reading list.

The conversation around the idea.

Links found in the discussion

S1: A $6 R1 competitor?

Claude Code is all you need

DreamFusion: Text-to-3D using 2D Diffusion

Yann LeCun, Geoffrey Hinton and Yoshua Bengio win Turing Award

Ask HN: What's the best paper you've read in 2020?

DOJ accuses Visa of monopoly that affects price of 'nearly everything’

LLMs can get "brain rot"

SmolGPT: A minimal PyTorch implementation for training a small LLM from scratch

Better Language Models and Their Implications

AI capex is so big that it's affecting economic statistics

Exploring LSTMs

The great software quality collapse or, how we normalized catastrophe

Ilya Sutskever: “If you learn all of these, you’ll know 90% of what matters”

How AlphaChip transformed computer chip design

Building an end-to-end Speech Recognition model in PyTorch

Don't post generated/AI-edited comments. HN is for conversation between humans.

Transformer: A Novel Neural Network Architecture for Language Understanding

I asked GPT-3 for the question to “42”

OpenAI Releases Largest GPT-2 Text Generation Model

Biological Function Emerges from Unsupervised Learning on 250M Protein Sequences

MDMA reopens child-like “critical periods” in the brain

Regularization is all you need: simple neural nets can excel on tabular data

Markov Chains Explained Visually (2014)

How the Brain Creates a Timeline of the Past

Show HN: Ecco – See what your NLP language model is “thinking”

Extracting Structured Data from Recipes Using Conditional Random Fields (2015)

Darwin Machines

The Illustrated Transformer (2018)

Tensor Product Attention Is All You Need

T5Gemma 2: The next generation of encoder-decoder models

Machine Learning Can't Handle Long-Term Time-Series Data

Windows 11 calls a zip file a 'postcode file' in UK English

Building a semantic search engine in Rust

Can Demis Hassabis save Google?

The Bitcoin whitepaper is hidden in every copy of macOS

TransMLA: Multi-head latent attention is all you need

Microsoft’s New MT-DNN Outperforms Google BERT

Why do we remember some life moments but not others?

Formal Algorithms for Transformers

ArXiv LaTeX Cleaner: Clean the LaTeX code of your paper to submit to ArXiv

Is A.I. The Death of I.P.?

Attention and Augmented Recurrent Neural Networks

New AI Training Technique Is Drastically Faster, Says Google

Transformer Attention is off by one

DLVM: A modern compiler framework for neural network DSLs

The potential of transformers in reinforcement learning

Reinforcement Pre-Training

Anthropic - Introducing 100K Token Context Windows, Around 75,000 Words

Trump sides with Musk on support for H-1B visas for foreign tech workers

How to install Windows 11 on a device that does not meet Windows 11 requirements

Ask HN: Can someone ELI5 Transformers and the “Attention is all we need” paper

Microsoft’s new text-to-speech model can duplicate anyone's voice in 3 seconds

Transformer: A Neural Network Architecture for Language Understanding (2017)

Textbooks are all you need

You Don't Know Jack about Application Performance

Dirtyfrag: Universal Linux LPE

We aren't close to creating a rapidly self-improving AI

Show HN: ArXiv-txt, LLM-friendly ArXiv papers

Strangely Accurate AI Predictions from Blurry Medical Scans Alarms Researchers

The Illustrated Transformer

If you replace the "x" with a "5" in an ArXiv URL, you get an HTML version

Deep Neural Networks – Attention is all you need (No recurrence or convolutions)

Scaffolded LLMs as natural language computers

What Are Transformer Models and How Do They Work?

Attention Is All You Need (Neural Networks)

Apple Sues OpenAI for Stealing Trade Secrets to Build AI Hardware

Google internally developed chatbots like ChatGPT years ago

Sparks of Artificial General Intelligence: Early Experiments with GPT-4

Show HN: Turn Any ArXiv Paper into a 200-Page Prerequisite Reading Book

Attention Is All You Need

Microsoft and OpenAI Working on ChatGPT-Powered Bing in Challenge to Google

Gitlab AI is going head to head with GitHub Copilot

Gemini Pro achieves accuracy slightly inferior to GPT 3.5 Turbo

Attention Is All You Need

Understanding and Coding the Self-Attention Mechanism of Large Language Models

Open source solution replicates ChatGPT training process

Attention Is All You Need

Attention Is All You Need