layer

Type Members

1. class BasicLayer extends Layer

   

   Layer: Basic, Fully-connected Layer

2. class DropoutLayer extends Layer

   

   Layer that drop-outs its input.

   Layer that drop-outs its input.

   This layer has a function of "pipeline" with drop-out possibility. Because dropping out neurons occurr in the hidden layer, we need some intermediate pipe that handle this feature. This layer only conveys its input to its output synapse if that output is alive.

3. class FullTensorLayer extends Rank3TensorLayer

   

   Layer: Basic, Fully-connected Rank 3 Tensor Layer.

   Layer: Basic, Fully-connected Rank 3 Tensor Layer.

   Note

         v0 = a column vector
         Q = Rank 3 Tensor with size out, in × in is its entry.
         L = Rank 3 Tensor with size out, 1 × in is its entry.
         b = out × 1 matrix.
   
         output = f( v0'.Q.v0 + L.v0 + b )
   

4. trait Layer extends (ScalarMatrix) ⇒ ScalarMatrix with Serializable

   

   Trait that describes layer-level computation

   Trait that describes layer-level computation

   Layer is an instance of ScalaMatrix => ScalaMatrix function. Therefore "layers" can be composed together.

5. class NormalizeLayer extends Layer

   

   Layer that normalizes its input.

6. abstract class Rank3TensorLayer extends Layer

   

   Layer: Basic, Fully-connected Rank 3 Tensor Layer.

   Layer: Basic, Fully-connected Rank 3 Tensor Layer.

   Note

         v0 = a column vector concatenate v2 after v1 (v11, v12, ... v1in1, v21, ...)
         Q = Rank 3 Tensor with size out, in1 × in2 is its entry.
         L = Rank 3 Tensor with size out, 1 × (in1 + in2) is its entry.
         b = out × 1 matrix.
   
         output = f( v1'.Q.v2 + L.v0 + b )
   

7. class ReconBasicLayer extends BasicLayer with Reconstructable

   

   Layer : Reconstructable Basic Layer

8. trait Reconstructable extends Layer

   

   Trait of Layer that can be used for autoencoder

9. class SplitTensorLayer extends Rank3TensorLayer

   

   Layer: Basic, Fully-connected Rank 3 Tensor Layer.

   Layer: Basic, Fully-connected Rank 3 Tensor Layer.

   Note

         v0 = a column vector concatenate v2 after v1 (v11, v12, ... v1in1, v21, ...)
         Q = Rank 3 Tensor with size out, in1 × in2 is its entry.
         L = Rank 3 Tensor with size out, 1 × (in1 + in2) is its entry.
         b = out × 1 matrix.
   
         output = f( v1'.Q.v2 + L.v0 + b )