a pair of input & output, such as 2 -> 3
an activation function to be applied
initial weight matrix for the case that it is restored from JSON (default: null)
inital bias matrix for the case that it is restored from JSON (default: null)
Backward computation.
Backward computation.
to be propagated ( dG / dF
is propagated from higher layer )
of this layer (in this case, x = entry of dX / dw
)
of this layer (in this case, y
)
propagated error (in this case, dG/dx
)
Let this layer have function F composed with function X(x) = W.x + b
and higher layer have function G.
Weight is updated with: dG/dW
and propagate dG/dx
For the computation, we only used denominator layout. (cf. Wikipedia Page of Matrix Computation) For the computation rules, see "Matrix Cookbook" from MIT.
Sugar: Forward computation.
Sugar: Forward computation. Calls apply(x)
input matrix
output matrix
weights for update
an activation function to be applied
an activation function to be applied
Forward computation
Forward computation
input matrix
output matrix
accumulated delta values
Number of Fan-ins
Number of Fan-ins
Number of output
Number of output
Translate this layer into JSON object (in Play! framework)
Translate this layer into JSON object (in Play! framework)
JSON object describes this layer
Layer: Basic, Fully-connected Layer