Abstract The number of iterations that this optimizer instance has been invoked for.
Abstract applyUpdates variables by using the computed gradients.
A mapping of variable name to its gradient value.
Executes f() and computes the gradient of the scalar output of f() with
respect to the list of trainable variables provided by varList. If no
list is provided, it defaults to all trainable variables.
The function to execute and whose output to use for computing gradients with respect to variables.
Optional varList: Variable<Rank>[]An optional list of variables to compute gradients with respect to. If specified, only the trainable variables in varList will have gradients computed with respect to. Defaults to all trainable variables.
Protected extractExtract the first element of the weight values and set it as the iterations counter variable of this instance of optimizer.
Weight values with the first element consumed and excluded.
Return the class name for this class to use in serialization contexts.
Generally speaking this will be the same thing that constructor.name would have returned. However, the class name needs to be robust against minification for serialization/deserialization to work properly.
There's also places such as initializers.VarianceScaling, where implementation details between different languages led to different class hierarchies and a non-leaf node is used for serialization purposes.
Abstract getExecutes f() and minimizes the scalar output of f() by computing
gradients of y with respect to the list of trainable variables provided by
varList. If no list is provided, it defaults to all trainable variables.
The function to execute and whose output to minimize.
Optional returnCost: booleanWhether to return the scalar cost value produced by
executing f().
Optional varList: Variable<Rank>[]An optional list of variables to update. If specified, only the trainable variables in varList will be updated by minimize. Defaults to all trainable variables.
Static fromGenerated using TypeDoc
Doc