definition

Feedforward computation versus training backpropagation

Using a trained network (e.g., ChatGPT inference) is purely a feedforward process where an input vector propagates layer by layer to an output, whereas training requires the back-and-forth of computing a loss on the output side and backpropagating it to update each layer's weights toward the input side.

definitionpending

Speaker

Anil Ananthaswamy

Evidence Quote

“when we use it, we're just using the feedforward part of it. But when you're training it, you have to keep doing this back and forth.”

Source

336 | Anil Ananthaswamy on the Mathematics of Neural Nets and AI— Sean Carroll's Mindscape
Created: 6/13/2026, 12:20:04 AM

Your notes

Loading notes...