weights for update
weights for update
weights
Activation Function
Activation Function
Forward computation
accumulated delta values
accumulated delta values
delta-weight
Translate this layer into JSON object (in Play! framework)
Translate this layer into JSON object (in Play! framework)
JSON object describes this layer
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
Trait that describes layer-level computation
Layer is an instance of ScalaMatrix => ScalaMatrix function. Therefore "layers" can be composed together.