Index

A B C D E F G H I K L M N O P Q R S T U V W X Z
All Classes and Interfaces|All Packages

B

BatchData - Class in mklab.JGNN.adhoc

BatchData(List<Tensor>, List<Tensor>) - Constructor for class mklab.JGNN.adhoc.BatchData

BatchOptimizer - Class in mklab.JGNN.nn.optimizers

Wraps an Optimizer by accumulating derivatives and calling Optimizer.update(Tensor, Tensor) with the average derivative after a fixed number of accumulations.

BatchOptimizer(Optimizer) - Constructor for class mklab.JGNN.nn.optimizers.BatchOptimizer

Initializes a BatchOptimizer that accumulates derivatives and updates them only when BatchOptimizer.updateAll() is called.

BatchOptimizer(Optimizer, long) - Constructor for class mklab.JGNN.nn.optimizers.BatchOptimizer

Initializes a BatchOptimizer that accumulates derivatives and updates them with BatchOptimizer.updateAll() after every fixed number of updates.

Benchmarks - Class in Unnamed Package

Benchmarks() - Constructor for class Benchmarks

BinaryCrossEntropy - Class in mklab.JGNN.nn.loss

Implements a binary cross-entropy Loss.
For more than one output dimensions use CategoricalCrossEntropy

BinaryCrossEntropy() - Constructor for class mklab.JGNN.nn.loss.BinaryCrossEntropy

Initializes binary cross entropy with 1.E-12 epsilon value.

BinaryCrossEntropy(double) - Constructor for class mklab.JGNN.nn.loss.BinaryCrossEntropy

Initializes binary cross entropy with and epsilon value to bound its outputs in the range [log(epsilon), -log(epsilon)] instead of (-inf, inf).

A B C D E F G H I K L M N O P Q R S T U V W X Z
All Classes and Interfaces|All Packages