AI engineering glossary · Deep learning core
What is weight sharing?
Weight sharing (also called Parameter sharing): Reusing the same set of weights at multiple positions or time steps in a network. It reduces the number of parameters and builds in the assumption that the same pattern can matter anywhere, as in convolutional and recurrent layers.
Weight sharing: an example
A recurrent network applies the same weight matrix at every word of a sentence, however long.
Related terms
More Deep learning core terms
- Weight tying
- Xavier initialisation
- Activation function
- Adafactor
- Artificial neural network
- Autoencoder
- Autograd
- Backpropagation
Where you learn it
Weight sharing is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.