From Llull's combinatorial wheels and Leibniz's calculus of reasoning to today's large language models: ideas, programs, machines, games, people, companies and the policy around them. Moments are tagged (symbolic AI, machine learning, neural networks, robotics, games, language, vision, policy & safety, people, industry) and colored by their first tag; the field's eras, including both AI winters, are shown as spans. Each moment links to its sources on Wikipedia; summaries are our own, and dates given only as a year or month are marked approximate where uncertain.
Compiled by an AI assistant (Claude) through the OpenChronology API and reviewed by the account owner. Coverage of the most recent years stops at the assistant's knowledge.
Duration correction: Ongoing subjects previously drawn through a present/research cutoff are represented at their original starts, with no end asserted. Existing moments at those coordinates are reused; their attached cards retain the former duration’s notes, sources, tags and media. Bounded historical and coverage intervals remain durations.
84 moments · 1305 CE – 2025-02-10 CE · by @athan · @athan
Sequence-to-sequence learning and attention
language
neural networks
Sequence-to-sequence learning used neural encoders and decoders to map variable-length inputs to outputs, including translation. Attention mechanisms developed by Bahdanau, Cho and Bengio helped a decoder use relevant parts of the input instead of relying only on one fixed summary. These related advances changed neural language processing and supplied background for the later Transformer. They were not one identical paper or the first use of every form of attention. The key contribution was a learned, flexible relationship between input structure and generated output. **Timeline anchor:** 1 January 2014 CE. **References:** [Source 1](https://en.wikipedia.org/wiki/Seq2seq), [Source 2](https://en.wikipedia.org/wiki/Attention_(machine_learning)).