Why is machine learning 'hard'? (2016) (ai.stanford.edu)

Screenshot of ai.stanford.edu: Why is machine learning 'hard'? (2016)

First screen, captured 2 years ago.

Looks similar

Screenshot of kaveland.no: Friends don't let friends export to CSV

Friends don't let friends export to CSV (kaveland.no)

207 points by lervag 2 years ago | 357 comments

Screenshot of ikkaro.net: TinyML: Ultra-low power machine learning

TinyML: Ultra-low power machine learning (ikkaro.net)

349 points by Gedxx 2 years ago | 84 comments

An Ikkaro blog article explaining TinyML, covering model compression techniques like pruning, quantization and distillation, tools, and uses on low-power devices.

tinyml embedded-ml microcontrollers quantization

Screenshot of jalammar.github.io: The Illustrated GPT-2: Visualizing Transformer Language Models (2019)

The Illustrated GPT-2: Visualizing Transformer Language Models (2019)(jalammar.github.io)

195 points by epberry 2 years ago | 5 comments

Screenshot of rnikhil.com: Attacks on machine learning models

Attacks on machine learning models (rnikhil.com)

84 points by whoami_nr 2 years ago | 26 comments

Screenshot of myme.no: Programming is hard

Programming is hard (myme.no)

85 points by ingve 3 years ago | 77 comments

Screenshot of mvakde.github.io: I trained a small transformer in 1.5hrs and it beats many LLMs

I trained a small transformer in 1.5hrs and it beats many LLMs (mvakde.github.io)

578 points by porridgeraisin 1 month ago | 149 comments

Personal blog post describing a small transformer trained from scratch in 1.5 hours on an RTX 5090 that scores 44% on ARC-AGI-1 for 67 cents.

arc-agi transformers benchmarks model-training

Looks similar

Friends don't let friends export to CSV(kaveland.no)

TinyML: Ultra-low power machine learning(ikkaro.net)

The Illustrated GPT-2: Visualizing Transformer Language Models (2019)(jalammar.github.io)

Attacks on machine learning models(rnikhil.com)

Programming is hard(myme.no)

I trained a small transformer in 1.5hrs and it beats many LLMs(mvakde.github.io)

Friends don't let friends export to CSV (kaveland.no)

TinyML: Ultra-low power machine learning (ikkaro.net)

Attacks on machine learning models (rnikhil.com)

Programming is hard (myme.no)

I trained a small transformer in 1.5hrs and it beats many LLMs (mvakde.github.io)