module = Mul(inputDimension)

Applies a single scaling factor to the incoming data, i.e. y= w x, where w is a scalar.

Example: 

y=torch.Tensor(5);  
mlp=nn.Sequential()
mlp:add(nn.Mul(5))

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:mul(math.pi);
 err=gradUpdate(mlp,x,y,nn.MSECriterion(),0.01)
end
print(mlp:get(1).weight)
gives the output: 
 3.1416
[torch.Tensor of dimension 1]
i.e. the network successfully learns the input x has been scaled by pi.