Early Stopping

Validation Set

प्रमाणीकरण सेट

Data used during training to tune settings and avoid overfitting before final testing.

Convergence

अभिसरण

The point at which further training stops meaningfully improving a model.

Distributed Training

वितरित तालिम

Training a model across many machines or chips at once to handle large workloads.

Dropout

ड्रपआउट

A regularization method that randomly disables neurons during training to reduce overfitting.

Learning Curve

सिकाइ वक्र

A plot showing how a model's performance changes as it sees more training data.

Overfitting

ओभरफिटिङ / अति-अनुकूलन

When a model learns the training data too closely, including noise, and fails on new data.

AUC

एयूसी

The area under the ROC curve summarizing classification performance as a single number.

Bagging

ब्यागिङ

Training many models on random data subsets and averaging them to reduce variance.