class StoppingRule extends AnyRef
The StoppingRule class provides a stopping rule to terminating the iterative
steps in an optimization early.
- Alphabetic
- By Inheritance
- StoppingRule
- AnyRef
- Any
- Hide All
- Show All
- Public
- Protected
Instance Constructors
- new StoppingRule(up_limit: Int = 4)
- up_limit
the stopping rule limit (number of increasing steps allowed)
Value Members
- def stopWhen(b: NetParams, sse: Double): (NetParams, Double)
Stop when too many steps have the cost measure (e.g., sse) increasing.
Stop when too many steps have the cost measure (e.g., sse) increasing. Signal a stopping condition by returning the best parameter vector, else null.
- b
the current parameter value (weights and biases)
- sse
the current value of cost measure (e.g., sum of sqaured errors)
- def stopWhen(b: VectoD, sse: Double): (VectoD, Double)
Stop when too many steps have the cost measure (e.g., sse) increasing.
Stop when too many steps have the cost measure (e.g., sse) increasing. Signal a stopping condition by returning the best parameter vector, else null.
- b
the current value of the parameter vector
- sse
the current value of cost measure (e.g., sum of sqaured errors)