I am currently taking a machine learning course and had a question about the update rule for $\theta$ in neural networks. In the discussion of previous learning algorithms, the professor defined: $$\theta := \theta - \alpha \frac{\partial J(\theta)}{\partial \theta}$$
In the discussion of ANN classifiers, however, there was never an explicitly defined update rule, which I took to mean that it was the same as previous algorithms. If someone could verify that this is the case, that would be great. Thanks.