Incorrect use of "epoch" in the Optimizing Model Parameters tutorial

[chrsigg]

From the first paragraph of the Optimizing Model Parameters tutorial:

in each iteration (called an epoch) the model makes a guess about the output, calculates the error in its guess (loss), collects the derivatives of the error with respect to its parameters (as we saw in the previous section), and optimizes these parameters using gradient descent.

What is described in this paragraph is a single optimization step. An epoch is a full pass over the dataset (see e.g. https://deepai.org/machine-learning-glossary-and-terms/epoch).

I propose to simply remove the "(called an epoch)" here, as the term is correctly used and explained later in the "Hyperparameters" section:

Number of Epochs - the number times to iterate over the dataset

cc @suraj813

[subramen]

Good catch! You are correct, that "epoch" was being used incorrectly in that statement. Thank you for bringing this up and helping to improve the quality of our tutorials :) If you see any other mistake, please raise an issue. If you know the fix, I'd encourage you to submit a PR and I'll be happy to merge your changes in.