module = CMul(inputDimension)

Applies a component-wise multiplication to the incoming data, i.e. y_i = w_i x_i.

Example: 

mlp=nn.Sequential()
mlp:add(nn.CMul(5))

y=torch.Tensor(5); 
sc=torch.Tensor(5); for i=1,5 do sc[i]=i; end -- scale input with this

function gradUpdate(mlp,x,y,criterion,learningRate) 
  local pred = mlp:forward(x)
  local err = criterion:forward(pred,y)
  local gradCriterion = criterion:backward(pred,y);
  mlp:zeroGradParameters();
  mlp:backward(x, gradCriterion);
  mlp:updateParameters(learningRate);
  return err
end

for i=1,10000 do
 x=lab.rand(5)
 y:copy(x); y:cmul(sc);
 err=gradUpdate(mlp,x,y,nn.MSECriterion(),0.01)
end
print(mlp:get(1).weight)
gives the output: 
 1.0000
 2.0000
 3.0000
 4.0000
 5.0000
[torch.Tensor of dimension 5]
i.e. the network successfully learns the input x has been scaled by those scaling factors to produce the output y.