Reproducibility

Experiment Tracking

प्रयोग ट्र्याकिङ

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

Batch Inference

ब्याच इन्फरेन्स

Running predictions on many inputs together rather than one at a time.

Caching

क्यासिङ

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

Carbon Footprint (AI)

कार्बन फुटप्रिन्ट (एआई)

The greenhouse-gas emissions caused by training and running AI systems.

Catastrophic Forgetting

विनाशकारी विस्मरण

When a model learning a new task abruptly loses its ability on previous tasks.

Common Sense Reasoning

सामान्य बुद्धि तर्क

The ability to make everyday assumptions humans take for granted, still hard for AI.

Coreference Resolution

सहसन्दर्भ समाधान

Determining which words in a text refer to the same entity, like 'she' and a name.

Data Leakage

डाटा चुहावट

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