The glossary
Every word you'll meet in AI and machine learning, explained in everyday language.
KL(q‖p) with p the data: it punishes q for putting weight where p has none, so q locks onto one mode.
Which fit is closer to p depends on which KL you ask. The next part measures both.
KL divergence at work · Forward against reverse KL, KL between normals, F.kl_div's argument order, a distillation loss with temperature, and a KL penalty against a base model. About 36 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.
Forward against reverse KL, KL between normals, F.kl_div's argument order, a distillation loss with temperature, and a KL penalty against a base model.
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