class Net(torch.nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.l1 = torch.nn.Linear(1, 1)
        self.optimizer = torch.optim.Adadelta(self.parameters())
        self.loss_function = torch.nn.MSELoss()

    def forward(self):
        return self.l1(torch.tensor([1], dtype=torch.float))

    def backward(self, loss):
        self.optimizer.zero_grad()
        loss.backward()
        if not self.l1.weight.grad is None:
            #(*) changing the grad to 0
            self.l1.weight.grad[0] = torch.tensor([0], dtype=torch.float)
        self.optimizer.step()