All Classes and Interfaces
Class
Description
A
ContextGenerator implementation for maxent decisions, assuming that the input
given to the BasicContextGenerator.getContext(String) method is a String containing contextual
predicates separated by spaces, for instance:A
GISModelReader that reads models from a binary format.A
GISModelWriter that writes models in a binary format.A
QNModelReader that reads models from a binary format.A
QNModelWriter that writes models in a binary format.Represents a generator of contexts for maxent decisions.
An interface for objects which can deliver a stream of training data to be
supplied to an EventStream.
Interface for a function.
A maximum entropy model which has been trained using the Generalized
Iterative Scaling (GIS) procedure.
The base class for readers of
GIS models.The base class for writers of
GIS models.An implementation of Generalized Iterative Scaling (GIS).
Performs line search to find a minimum.
Represents a
LineSearch result encapsulating the relevant data
at a point in time during computation.A
StopCriteria implementation to identify whether the
difference between the log likelihood of current and previous iteration is under the defined threshold.Evaluates negative log-likelihood and its gradient from
DataIndexer.Evaluates
negative log-likelihood and
its gradient in parallel.Implementation of the
Limited memory Broyden-Fletcher-Goldfarb-Shanno algorithm (L-BFGS) which
supports L1-, L2-regularization and Elastic Net for solving convex optimization problems.
Evaluate the quality of training parameters.
L2-regularized objective
Function.A
maximum entropy model which has been trained via the
L-BFGS algorithm ,
which belongs to the group of Quasi Newton (QN) algorithms.The base class for readers of
QN models.The base class for writers of
models.A Maxent model
trainer using the
L-BFGS algorithm.Class for real-valued
events as an
event stream.
.