hAIgopala › AI terms › How Bit Really Learns › Day 10

Loss Function

Neural Networks & Deep LearningChapter 3: Inside the BrainTerm 44 of 253

Measures how wrong the model's predictions are; training minimises it.

At Sunrise School

Gopal asks

How do we measure Bit's mistakes while learning?

Bit answers

The loss function. If I say Transport but the label is Fees, the loss is high. Training pushes the loss down.

In the real world

The exam score you try to improve.

Watch the short

Short coming soonSeason 2 · Day 10Follow @haigopala

Quick check

Quick check. Is a high loss good? 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