
zero-shot learning
/ˈzɪəroʊ ʃɒt ˌlɜːrnɪŋ/
Performing tasks without any task-specific training examples
“Zero-shot learning enables the model to classify categories it hasn't seen.”
Etymology — Modern compound; `zero` from Arabic `sifr` (empty) + `shot` (attempt) + `learning` from Old English `leornian`