Training and running modern machine learning models, especially large deep learning and generative models, requires enormous amounts of computation, mostly large matrix and vector math. General-purpose CPUs can do this work, but slowly. Specialized hardware called accelerators speeds it up dramatically, and access to accelerators at scale is one reason organizations use the cloud for AI.
Free account
Keep reading for free
Create a free StudyToCert account to read the rest of this lesson: 4 more sections, 4 key terms, a real-world example, an exam tip and self-check questions. Every lesson, lab and practice test is free with an account.