In-Context Learning

Few-Shot Learning

फ्यु-सट सिकाइ

Guiding a model to perform a task by showing it just a few examples in the prompt.

Next Token Prediction

अर्को टोकन अनुमान

The core training task of LLMs: predicting the next piece of text given prior context.

Active Learning

सक्रिय सिकाइ

A method where the model selects the most useful examples for humans to label.

Artificial General Intelligence (AGI)

कृत्रिम सामान्य बुद्धिमत्ता

A hypothetical AI that can understand and perform any intellectual task a human can, across many domains.

Artificial Intelligence (AI)

कृत्रिम बुद्धिमत्ता

The field of building machines and software that can perform tasks normally requiring human intelligence, such as reasoning, learning, and decision-making.

Catastrophic Forgetting

विनाशकारी विस्मरण

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

Federated Learning

फेडरेटेड लर्निङ

Training a shared model across many devices without moving their private data to a server.

Generalization

सामान्यीकरण

A model's ability to perform well on new, unseen data rather than just memorized examples.