Checkpoint

Dropout

ड्रपआउट

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

Gradient Clipping

ग्र्याडियन्ट क्लिपिङ

Capping gradient size during training to prevent unstable, exploding updates.

Parameter

प्यारामिटर

A value inside a model (like a weight) learned from data during training.

Validation Set

प्रमाणीकरण सेट

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

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.