AI Glossary
Backpropagation
What is Backpropagation?
The algorithm used to train neural networks by computing gradients of the loss function with respect to model weights, then adjusting those weights to reduce error. Backpropagation works backwards through the network layers using the chain rule of calculus. Understanding it helps professionals grasp why LLMs require massive compute resources to train.
Example in practice
When an AI company reports that training a new model required 10,000 GPU-days, that compute cost is almost entirely driven by running backpropagation across billions of parameters on trillions of training tokens.
Learn more
See Backpropagation applied in a professional context through this free course.
AI Fundamentals for Professionals →