AI Glossary Term

What is Compute?

Definition

The processing resources required to train and run models, often measured in FLOPS or GPU hours.

Related terms

Inference-Time Compute

The amount of processing power consumed while producing each response.

The extra cost in time, compute, or product velocity required to make systems safer and more controllable.

Convolutional Neural Network (CNN)

A neural architecture optimized for processing grid-like data such as images.

Cross-Entropy Loss

A common objective function used to train classification models by penalizing incorrect probabilities.

Confidence Interval

A statistical range that likely contains the true value of a measured model metric.

A software system that can observe, reason, and take actions to achieve a goal, often using tools and memory.

Learn more in our free guides

Computer Vision Chinchilla Compute-Optimal Training Test-Time Compute Scaling Computer-Using Agents

Browse the full AI Glossary Explore all free AI guides