4
votes
Accepted
Why does MNIST provide only a training and a test set and not a validation set as well?
The test set should never be seen and ran once at the end of training.
The validation set is used to help you select hyperparameters and it would be cheating to tune your model on the test set because ...
- 56
3
votes
How can a neural network distinguish a rotated 6 and 9 digits?
I think by writing left to right people create clockwise and counterclockwise patterns in the rounded parts of their typography.
For example, I think it'd be pretty unusual to write a 9 like this --&...
- 91
3
votes
How can a convnet learn with a 3x3 output layer?
I'm going to assume that what you posted is the output of something like model.summary() from TensorFlow/Keras. With that assumption, (None, 3, 3, 64) is the output shape. We can ignore the None, as ...
- 41
2
votes
Can I use 4 neurons for output layer to classify hand written digit?
One problem that I see is that you can no longer use the cross-entropy loss function for training, or at least I am not sure how you could do it. This cost function has many advantages, one of them ...
- 288
1
vote
Can I use 4 neurons for output layer to classify hand written digit?
I believe it is because when using the binary output, it makes the neurons dependent on each other, but technically it should not be, because it complicates two problems:
The first problem is how ...
- 1,027
1
vote
Why do we subtract logsumexp from the outputs of this neural network?
It's apparently for numerical stability. From the Wikipedia page for LogSumExp:
A common purpose of using log-domain computations is to increase accuracy and avoid underflow and overflow problems ...
- 111
1
vote
Can I use 4 neurons for output layer to classify hand written digit?
Of course you can but I'd not recommend doing this way.
First - it is not part of ML because it is straight logic and should not be learned, so I don't think backpropagation or other algorithms ...
- 121
1
vote
Accepted
Are the "artifacts" in select Keras MNIST training images really there or is my download corrupt?
There are many versions of MNIST digits now, and some of them are corrupted, binarized, or otherwise altered (see TensorFlow datasets) intentionally; but I don't think the keras MNIST digits has these ...
- 882
1
vote
How can I use my neural network model, trained on MNIST database, on "real word" digits such as my handwritten digits?
Can I test my model on other digits, for example I write the digit 7 on a paper with my pen and check whether my model would recognize it or not? How can I do it?
Yes, definitely. One of the main ...
- 882
1
vote
How can a neural network distinguish a rotated 6 and 9 digits?
"... since from the view of human perception 6 rotated by 180 degrees is equivalent to 9 and vice versa.".
Only with some typefaces, and almost never with handwritten text; someone would ...
- 608
1
vote
Can neural networks learn noise?
What explains the apparent 'mirroring' of the graphs on the RHS,
The model starts untrained and no better than random guessing (the baseline). As the training progresses, the model does better than ...
- 26.6k
1
vote
Accepted
MNIST with fewer pixels?
Sklearn has digit dataset with images of size $8 \times 8$:
Classes
10
Samples per class
~180
Samples total
1797
Dimensionality
64
Features
integers 0-16
- 2,194
Only top scored, non community-wiki answers of a minimum length are eligible