deep

A Neural Network implementation with Scala, Breeze & Spark

Example:

// Define 2 -> 4 -> 1 Layered, Fully connected network.
       val net = Network(Sigmoid, 2, 4, 1)

        // Define Manipulation Type. VectorType, AEType, RAEType, and URAEType.
        val operation = new VectorType(
           corrupt = GaussianCorruption(variance = 0.1)
        )

       // Define Training Style. SingleThreadTrainStyle vs DistBeliefTrainStyle
        val style = new SingleThreadTrainStyle(
          net = net,
          algorithm = new StochasticGradientDescent(l2decay = 0.0001),
           make = operation,
          param = SimpleTrainingCriteria(miniBatch = 8))

       // Define Trainer
       val train = new Trainer(
          style = style,
          stops = StoppingCriteria(maxIter = 100000))

       // Do Train
       train.train(set, valid)

Linear Supertypes

AnyRef, Any

Value Members

package fn

Package for various functions.
package layer

Package for layer implementation
package network

Package for network structure
package rec

Package object for DAG
package train

Package for training.
package wordvec

Package for WordEmbedding training (Unstable)

package deep

Value Members

package fn

package layer

package network

package rec

package train

package wordvec

Inherited from AnyRef

Inherited from Any

Ungrouped