The glossary
Every word you'll meet in AI and machine learning, explained in everyday language.
In retrieval, the share of queries whose right answer is among the top k results.
The standard score is recall at k, written R@k: the share of queries whose right answer is among the top k results. R@1 asks for the exact match in first place. R@5 forgives a near miss.
Press Next. Retrieval reads a column; the loss pushes the diagonal up and everything else down.
Image-text models in depth: retrieval, negatives and limits · How to test a shared image-text space with recall at k, what the rest of the batch teaches, what hard and false negatives do, and why a similarity score can't see word order, counts or "no". 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.
How to test a shared image-text space with recall at k, what the rest of the batch teaches, what hard and false negatives do, and why a similarity score can't see word order, counts or "no".
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