Glossary entry
एटेन्सन मेकानिज्म / ध्यान संयन्त्र
Definition (English)
A technique that lets a model focus on the most relevant parts of the input.
अर्थ (नेपालीमा)
मोडेललाई इनपुटको सबैभन्दा सान्दर्भिक भागमा ध्यान दिन सक्ने बनाउने प्रविधि।
Related terms
Feature Selection
फिचर छनोट
Choosing the most relevant input features and discarding the rest to improve a model.
Cross-Validation
क्रस-भ्यालिडेसन
A technique that splits data into multiple parts to test a model more reliably.
Principal Component Analysis (PCA)
प्रमुख घटक विश्लेषण
A technique that reduces many features into a few that capture most of the variation.
Reranking
रिर्याङ्किङ
Reordering retrieved results so the most relevant ones appear first.
Self-Attention
स्व-एटेन्सन
A mechanism letting each part of a sequence weigh the importance of every other part.
Transformer
ट्रान्सफर्मर
A neural network architecture using attention that powers most modern language models.
Active Learning
सक्रिय सिकाइ
A method where the model selects the most useful examples for humans to label.
Batch Normalization
ब्याच नर्मलाइजेसन
A technique that stabilizes and speeds up training by normalizing layer inputs.