Cross-entropy: why a confident wrong answer costs so much

Set three predicted probabilities against the answers 1, 0, 1: the loss is -log of the chance given to the truth. Drag toward a confident mistake and the cost climbs without bound.

This page sets no cookie and sends nothing anywhere.

Where the numbers come from

gHashTag/t27 specs/ml/loss/binary_crossentropy_loss.t27 (t27 master 239b4b059): every value on the page is its fn bodies, compiled to wasm (logic.js)
Course 10 of t27.ai, neural-networks (gHashTag/trinity#1695): lesson 14 opens this widget

This widget's .t27 source · All widgets