Backprop zeroing on FullyConnLayer

I'm curious why the input gradients are zero'd out in FullyConnLayer.backward() and not the biases and filter gradients.

So zero out input, filter and bias gradients like this:

```
backward: function() {
var V = this.in_act;
V.dw = global.zeros(V.w.length); // zero out the gradient in input Vol

// compute gradient wrt weights and data
for(var i=0;i