Reuse of one learnable parameter in multiple computational positions. In a convolution this reduces parameter count and imposes translation equivariance away from boundary effects.

Ancestors (8)

  1. Neural network
  2. Statistical learning
  3. Statistical modelling
  4. Statistical model
  5. Probability and statistics
  6. Area of mathematics
  7. Mathematics
  8. Home

Incoming links (1)

View article source

Discussion (0)

New discussion

There are no discussions about this article yet.

Articles by others on the same topic (0)

There are currently no matching articles.
See all articles in the same topic Create my own version