Optimization · Level 2 of 5
Saddle Point
A stationary point that is not a local minimum or maximum.
The function can rise in some directions and fall in others.
Example
A loss surface curves upward along one axis and downward along another.
Listen to the definition and example
Audio transcript
Saddle Point. A stationary point that is not a local minimum or maximum. The function can rise in some directions and fall in others. For example: A loss surface curves upward along one axis and downward along another.
Explore this concept
Why it matters
This helps you understand what parameter updates are trying to improve and when they can fail.
Start with
Related concepts
Quick recall question
Try answering before looking back at the definition.