Glossary entry
ग्र्याडियन्ट बुस्टिङ
Definition (English)
An ensemble technique that builds models sequentially, each correcting the previous one's errors.
अर्थ (नेपालीमा)
क्रमशः मोडेल बनाउने समूह विधि, जहाँ प्रत्येकले अघिल्लोको त्रुटि सच्याउँछ।
Related terms
Ensemble Learning
समूह सिकाइ
Combining multiple models to produce a stronger overall prediction.
XGBoost
एक्सजीबुस्ट
A fast, popular gradient boosting library known for strong performance on tabular data.
Adam Optimizer
एडम अप्टिमाइजर
A widely used optimizer that adapts the learning rate for each parameter.
API
एपीआई
A defined way for software programs to communicate and use each other's features.
Attention Mechanism
एटेन्सन मेकानिज्म / ध्यान संयन्त्र
A technique that lets a model focus on the most relevant parts of the input.
Autoregressive
अटोरिग्रेसिभ
Generating output one token at a time, each based on all the tokens produced before it.
Bagging
ब्यागिङ
Training many models on random data subsets and averaging them to reduce variance.
Batch Normalization
ब्याच नर्मलाइजेसन
A technique that stabilizes and speeds up training by normalizing layer inputs.