Convert the writables to a sequence (3d) data set, and also return the mask array (if necessary)

Read a datavec schema and record set from the given arrow file.

Convert the given DataFrame to a sequence
Note: It is assumed here that the DataFrame has been created by DataFrames.toDataFrameSequence(Schema, JavaRDD).

Query all with the distances sorted by index

Get the sorted distances given the query vector, input data, given the list of possible search candidates

For use during inference.

Loads an in memory cache from the given input stream (sets syn0 and the vocab).

Converts a treebank node to a tree

Feed forward the input mask array, setting in the layer as appropriate.

Do backward pass

Sample the hidden distribution given the visible

PreOutput method that also returns the im2col2d array (if being called for backprop), as this can be re-used instead of being calculated again.

Calculate gradients and errors.

Computes a gaussian kernel given a vector of squared distance distances

As per TrainingWorker.getFinalResult(ComputationGraph) but used when SparkTrainingStats are being collected

As per TrainingWorker.processMinibatch(DataSet, ComputationGraph, boolean) but used when SparkTrainingStats are being collected

As per TrainingWorker.processMinibatch(MultiDataSet, ComputationGraph, boolean) but used when SparkTrainingStats are being collected

Deprecated. 

Returns a list of words associated with the document and the associated labels

Iterate over each document with a label

Extract out the last time steps (2d array from 3d array input) accounting for the mask layer, if present.

Restore a ComputationGraph and Normalizer (if present - null if not) from the InputStream.

Restore a MultiLayerNetwork and Normalizer (if present - null if not) from the InputStream.

Returns a Set view of the keys contained in this map.

Associates the specified value with the specified key in this map (optional operation).

Copies all of the mappings from the specified map to this map (optional operation).

Convert a map with a set of entries of type K for key and V for value in to a list of Pair

For each key in left and right, cogroup returns the list of values as a pair for each value present in left as well as right.

Read all of the events starting at a specific file offset

This method creates long shapeInformation buffer, based on shape & order being passed in

This method creates long shapeInformation buffer, based on shape being passed in

This method creates long shapeInformation buffer, based on detailed shape info being passed in

Get an array of INDArrays (2d) all with the specified shape.

Test utility to sweep shapes given a rank Given a rank will generate random test matrices that will cover all cases of a shape with a '1' anywhere in the shape as well a shape with random ints that are not 0 or 1 eg. rank 2: 1,1; 1,2; 2,1; 2,2; 3,4 Motivated by TADs that often hit bugs when a "1" occurs as the size of a dimension