Multi-Armed Bandit

Optimization

अनुकूलन

Finding the best solution among many options according to some objective.

Top-p (Nucleus) Sampling

टप-पी स्याम्पलिङ

Choosing the next word from the smallest set of options whose probabilities add up to p.

Agentic AI

एजेन्टिक एआई

AI that autonomously plans and executes multi-step tasks using tools and feedback.

Algorithm

एल्गोरिदम / कार्यविधि

A step-by-step set of instructions a computer follows to solve a problem or complete a task.

Breadth-First Search

ब्रेथ-फर्स्ट सर्च

A search method that explores all options at one level before going deeper.

Cost Function

लागत फंक्सन

A function measuring total model error that training tries to minimize.

Dialogue System

संवाद प्रणाली

A system designed to hold multi-turn conversations with users.

Feature Selection

फिचर छनोट

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