Compute mapping for x
Compute mapping for x
the input matrix. Before application, input should be summed already.
value of f(x)
Compute differentiation value of this function at f(x) = fx
Compute differentiation value of this function at f(x) = fx
the output of this function
differentiation value at f(x) = fx
, which should be an square, diagonal matrix
Initialize the weight matrix
Initialize the weight matrix
the number of fan-in i.e. the number of neurons in previous layer
the number of fan-out i.e. the number of neurons in next layer
the number of rows of resulting matrix (Default 0)
the number of cols of resulting matrix (Default 0)
the initialized weight matrix
Trait that describes an activation function for each layer
Because these activation functions can be shared, we recommend to make inherited one as an object.