2

The problem is that numbers are not invariant to rotations. For example, see what happens when you rotate a 4 in steps of 90 degrees: So unless your task includes recognizing numbers which are written sideways or upside-down this does not provide a proper data augmentation.


1

In somewhat of a response to your comment to Sammy’s post, the problem doesn’t restrict to five-degree rotations. The problem allows for all rotations. An $8$ rotated 90 degrees is $\infty$ and no longer an $8$. Don’t train your neural net to see an $\infty$ and call it $8$. A $6$ rotated 180 degrees is a $9$; a $9$ rotated 180 degrees is a $6$. Don’t ...


1

This is because of the loss assumption is the (Mean) Squared Error $\mathcal{L} = (\hat{y} - y)^2$ and the derivative is $$ \frac{\partial}{\partial \hat{y}} \mathcal{L} = 2 (\hat{y} - y) $$ which is then passed "backward" for use in the chain rule.


1

Q1: I do not really understand how the situation in your Q1 is possible - I would expect an error to be thrown about as a mismatch in shape. For example, when I change the number of classes in the final dense layer, I do indeed get an error. model = Sequential() model.add(Conv2D(32, kernel_size=(3, 3), activation='relu', ...


1

I think the comment is true for any kind of network where the neuron has a linear transformation function and there is no activation. Convolution is just a special case of linear transformation. Basically, if your first layer outputs linear combinations of your features, and the second layer outputs linear combinations of the first layer outputs, then the ...


1

Yes, testing data should follow the same preprocessing as the training data. Otherwise, testing data will have nothing comparable with what the algorithm learned, leading to (very) bad performances. note: In Sklearn, the Pipeline class helps you to respect the fundamentals of ML modeling like data leakage and applying the same transformations to train and ...


1

I once described them (AI/ML methods in general) to a "senior" mechanical engineer (who really didn't get it, so hated it on principle, and was unfortunately in a position of influence): It's basically a look up table, interpolating between known data points. Except, unlike other interpolants like 'linear', 'nearest neighbour' or 'cubic', the ...


Only top voted, non community-wiki answers of a minimum length are eligible