WeightDecayStep¶
Chainable step that applies weight decay (analogous to l2 regularization) to the parameters.
This is typically applied after gradients have been scaled by criteria such as past gradient updates, but is applied before scaling by the learning rate, so that the learning rate does not change the ratio of the weight decay to the gradient update. The weight decay can be used in conjunction with a mask data structure that has the same nested structure as the weights being optimized, but which contains booleans indicating which weights should be decayed. Version 0.2.0
Ports/Properties¶
gradients¶
Gradients to be transformed.
weights¶
Optional current weights.
state¶
Explicit state of the node.
weight_decay_mask¶
Mask structure for the weight decay.
decay_rate¶
Weight decay rate. This is typically a small value, such as 1e-4.
set_breakpoint¶
Set a breakpoint on this node. If this is enabled, your debugger (if one is attached) will trigger a breakpoint.
metadata¶
User-definable meta-data associated with the node. Usually reserved for technical purposes.