hAIgopala › AI terms › How Bit Really Learns › Day 11

Backpropagation

Neural Networks & Deep LearningChapter 3: Inside the BrainTerm 46 of 253

Method to calculate how much each weight contributed to the error, so it can be corrected.

At Sunrise School

Gopal asks

Which weights caused the mistake?

Bit answers

Backpropagation sends the error backwards through the layers, telling each weight how much it was to blame.

In the real world

Tracing back who caused the mistake.

Watch the short

Short coming soonSeason 2 · Day 11Follow @haigopala

Quick check

Quick check. Does the error travel from the output back towards the input? Yes or no?

Practise it

Try this term and all 253 others in the free Model Training Arena.

Open the Arena →

Follow Bit daily: YouTube English · తెలుగు · हिंदी  |  Instagram English · తెలుగు · हिंदी