Glossary entry
Convergence
अभिसरण
Definition (English)
The point at which further training stops meaningfully improving a model.
अर्थ (नेपालीमा)
थप तालिमले मोडेल उल्लेख्य रूपमा नसुधार्ने बिन्दु।
Related terms
Other terms related to Convergence.
-
Early Stopping
अर्ली स्टपिङ
Halting training once validation performance stops improving to avoid overfitting.
-
Fine-Tuning
फाइन-ट्युनिङ
Further training a pre-trained model on specific data to specialize it for a task.
-
Bagging
ब्यागिङ
Training many models on random data subsets and averaging them to reduce variance.
-
Batch
ब्याच
A small subset of training data processed together in one step of training.
-
Batch Normalization
ब्याच नर्मलाइजेसन
A technique that stabilizes and speeds up training by normalizing layer inputs.
-
Bias (in AI)
पूर्वाग्रह (एआईमा)
Systematic unfairness in AI outputs, often reflecting biases present in training data.
-
Carbon Footprint (AI)
कार्बन फुटप्रिन्ट (एआई)
The greenhouse-gas emissions caused by training and running AI systems.
-
Chain-of-Thought
चेन-अफ-थट / विचार शृङ्खला
Prompting a model to reason step by step, improving accuracy on complex problems.