# fit method from NeuralNetwork class which calls layers' backward method
def fit(self, X, y, n_epochs=1000):
  self._initialize(X)
  losses = []
  for _ in range(n_epochs):
    last_output = X
      for layer in self.layers:
        last_output = layer.forward(last_output)

        loss = self.loss(last_output, y)
        losses.append(loss)
        last_d = self.dloss(last_output, y)

        for layer in reversed(self.layers):
            last_d = layer.backward(last_d, self.lr)

        print(f"Epoch: {_}; Loss: {loss};")

    return losses

#backward method for backpropagation in Dense class
def backward(self, last_derivative, lr):
  """
  Parameters
  - last_derivative : derivative from the previous layer
  - lr (learning rate) : determines how big changes are made to network's weights

  """
  w = self.weights

  dloss_1 = self.dactivate(last_derivative)
  d_w = np.dot(self.layer_input.T, dloss_1)

  self.weights -= -np.dot(lr, d_w)

  return np.dot(w, dloss_1.T)

# The problem is:
""" Gradient should point to the highest direction so I should substract it from weights, but then the loss increases. What's wrong? (I use self.weights -= -np.dot(...) because the loss decreases when it shouldn't)