The glossary
Every word you'll meet in AI and machine learning, explained in everyday language.
In contrastive training, the passages that belong to the other questions in a batch, used as wrong answers at no cost in labeling.
Tuning an embedding model for retrieval · When search fails on your own vocabulary: train an adapter with a contrastive loss on question and passage pairs, test on held-out passages, use batch size and hard negatives, and measure what tuning costs elsewhere. About 45 minutes.
1286 terms in the glossary, each with the lesson that teaches it.
Every word you'll meet in AI and machine learning, explained in everyday language.
When search fails on your own vocabulary: train an adapter with a contrastive loss on question and passage pairs, test on held-out passages, use batch size and hard negatives, and measure what tuning costs elsewhere.
Never trained an AI? Teach a small one to write, right in your browser. It takes about 20 seconds and needs no account. Teach it to write