hAIgopala › AI terms › Build Bit in 30 Days › Day 7

Gradient Descent

Neural Networks & Deep LearningChapter 3: Inside the BrainTerm 45 of 253

Optimisation method: take small steps in the direction that reduces error.

At Sunrise School

Gopal asks

How does training reduce the loss?

Bit answers

Gradient descent: small downhill steps on the error curve. Each step nudges the weights so the next answer is a little better.

In the real world

Walking downhill in fog, one step at a time.

Watch the short

Short coming soonSeason 1 · Day 7Follow @haigopala

Quick check

Quick check. Should every step be as big as possible? 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