Why gradInput of nn.Mul is computed by gradOutput add by weight rather than multiply by weight?

[ChunyanZhao]

I am confused by the function, and I think that the gradInput should be computed by gradInput = self.weight[1] * gradOutput rather than gradInput = self.weight[1] + gradOutput.

nn/Mul.lua

Lines 29 to 34 in 8726825

	function Mul:updateGradInput(input, gradOutput)
	self.gradInput:resizeAs(input):zero()
	self.gradInput:add(self.weight[1], gradOutput)
	return self.gradInput
	end