AdditiveNoiseStep¶
Chainable step that adds Gaussian noise to the gradients.
This can improve convergence and mitigate overfitting in some deep networks. Version 0.2.0
Ports/Properties¶
gradients¶
Gradients to be transformed.
weights¶
Optional current weights.
state¶
Explicit state of the node.
eta¶
Initial variance for the Gaussian noise added to gradients.
gamma¶
A parameter controlling the annealing of noise over time, the variance decays according to (1+t)^-gamma.
seed¶
A seed for the pseudo-random number generation.
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.