Beta. Content is under active construction and has not been peer-reviewed. Report errors on
GitHub
.
Disclaimer
Theorem
Path
Curriculum
Paths
Demos
Diagnostic
Search
Quiz Hub
/
Convolutional Neural Networks
Convolutional Neural Networks
1 questions
Difficulty 3-3
View topic
Foundation
0 / 1
1 foundation
Adapts to your performance
1 / 1
foundation (3/10)
conceptual
Convolutional layers are translation equivariant: shifting the input shifts the output by the same amount. What property does the pooling layer add?
Hide and think first
A.
Pooling only reduces computation; it has no effect on invariance properties
B.
Scale invariance: pooling makes the network handle different object sizes
C.
Approximate translation invariance: small input shifts produce identical or nearly identical pooled outputs
D.
Rotation equivariance: pooling makes the network invariant to rotations
Submit Answer