|
|
|
|
|
|
by btown
984 days ago
|
|
|
In a way, this could be considered adding a speculative transformation of the input as part of the input to some layer, and the network deciding whether or not to use that transformation. It would be akin to a convolution layer in a CNN, albeit far more domain-specific. But I’m not sure how much research has been done on weird layers like this! |
|
|