layer

Type Members

1. class BasicLayer extends TransformLayer

   

   Layer: Basic, Fully-connected Layer

2. 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 )
   

3. trait InputLayer[In, OutInfo] extends Layer[In, OutInfo]

   

   Trait for input layer.

   Trait for input layer.

   In

   Input type

   OutInfo

   Output type to store.

4. trait Layer[In, OutInfo] extends Serializable with KryoSerializable

   

   Trait of layer.

   Trait of layer.

   In

   Input type

   OutInfo

   Output type to store.

5. class LinearTransformLayer extends TransformLayer

   

   Layer: Basic, Fully-connected Layer without bias.

6. trait NetworkConcatLayer[X] extends InputLayer[Array[X], DataVec]

   

   Layer for network concatenation.

   Layer for network concatenation.

   X

   Input type of networks.

7. class RBFLayer extends TransformLayer

   

   Layer : An Radial Basis Function Layer, with its radial basis.

   Layer : An Radial Basis Function Layer, with its radial basis.

   Note

   This is a RBF layer, mainly the same with 3-phrase RBF in paper Three learning phrases for radial-basis-function networks

8. abstract class Rank3TensorLayer extends TransformLayer

   

   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 )
   

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 )
   

10. trait TransformLayer extends Layer[DataVec, DataVec]

    

    Trait for hidden/output layer.

11. class TwoPhraseRBFLayer extends TransformLayer

    

    Layer : An Radial Basis Function Layer, with its radial basis.

12. class VectorRBFLayer extends TransformLayer

    

    Layer : An Radial Basis Function Layer, with its radial basis.

    Layer : An Radial Basis Function Layer, with its radial basis.

    Note

    This is a RBF layer, mainly the same with 3-phrase RBF in paper Three learning phrases for radial-basis-function networks