Lesson 5
20 min

Why GPUs Run AI: The Hardware Behind the Magic

Quick Summary

Graphics processing units, or GPUs, can perform many similar calculations in parallel. That makes them well suited to the matrix operations used throughout neural-network training and inference.

What you will learn
  • ·Explain why parallel computation benefits AI workloads
  • ·Distinguish training from inference
  • ·Connect hardware choices to cost, speed, and capacity