Outlier

Caching

क्यासिङ

Storing frequently used results so they can be returned quickly without recomputing.

Convergence

अभिसरण

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

Data Leakage

डाटा चुहावट

When information from outside the training set sneaks in, giving misleadingly good results.

Experiment Tracking

प्रयोग ट्र्याकिङ

Recording the settings, data, and results of model experiments for comparison.

Feature Selection

फिचर छनोट

Choosing the most relevant input features and discarding the rest to improve a model.

FLOPS

फ्लप्स (FLOPS)

Floating-point operations per second, a measure of computing performance.

k-Nearest Neighbors (k-NN)

के-निकटतम छिमेकी

A method that classifies a new point based on the labels of its closest neighbors.

Keypoint

कीपोइन्ट / मुख्य बिन्दु

A distinctive point in an image used to match or track features.