Questions tagged [mnist]
For questions that involve the MNIST dataset, but note that questions asking for datasets are off-topic here.
12
questions
0
votes
0
answers
10
views
Why do we subtract logsumexp from the outputs of this neural network?
I'm trying to understand this tutorial for Jax.
Here's an excerpt. It's for a neural net that is designed to classify MNIST images:
...
- 121
0
votes
0
answers
19
views
How to optimize input image tensor, to best fit image classifier, for specific target class?
Assume that we got pretrained image classifier, and we want to then optimize some input image tensor for it, that for given class, the output of classifier will match. How to do this for example in ...
- 101
0
votes
1
answer
39
views
How can a convnet learn with a 3x3 output layer?
I was studying the "Deep Learning with Python" book, I came across this MNIST example and this is how the last conv2d layer looks like:
...
- 101
0
votes
0
answers
48
views
What model to train to restore MNIST test dataset
I came across this problem, and am not sure where to start. What model would work best for this problem and why?
Imagine the digits in the test set of the MNIST dataset (http://yann.lecun.com/exdb/...
6
votes
0
answers
93
views
How can a neural network distinguish a rotated 6 and 9 digits?
Rotated MNIST is a popular dataset for benchmarking models equivariant to rotations on $\mathbb{R}^2$, described by $SO(2)$ group or its discrete subgroups like $\mathbb{Z}^{n}$:
Group equivariant ...
- 1,824
3
votes
1
answer
63
views
Can neural networks learn noise?
I'm interested in the following graphs. A neural network was trained to recognise digits from the MNIST dataset and then the labels were randomly shuffled and the following behaviour was observed. ...
- 131
-2
votes
1
answer
54
views
MNIST with fewer pixels? [closed]
MNIST images are 28x28 pixels. Perhaps a silly question: is there anything like MNIST, but whose images have fewer pixels?
0
votes
0
answers
92
views
Why would my neural network have either an accuracy of 90% or 10% on the validation data, given a random initialization?
I'm making a custom neural network framework (in C++, if that is of any help). When I train the model on MNIST, depending on how happy the network is feeling, it'll give me either 90%+ accuracy, or ...
- 115
1
vote
0
answers
238
views
Why does the VAE using a KL-divergence with a non-standard mean does not produce good images?
I know I can make a VAE do generation with a mean of 0 and std-dev of 1.
I tested it with the following loss function:
...
- 43
2
votes
0
answers
64
views
Statistical method for selecting features for classification
I'm working on a classifier for the famous MNIST handwritten data set.
I want to create a few features on my own, and I want to be able to estimate which feature might perform better before actually ...
0
votes
2
answers
271
views
What is the right way to train a generator in a GAN?
I am not fully understanding how to train a GAN's generator. I have a few questions below, but let me first describe what I am doing.
I am using the MNIST dataset.
I generate a batch of random images ...
0
votes
0
answers
118
views
Is there a way to reduce the RMSE error when training a neural network to recognise MNIST digits using ANFIS?
I wanted to build a digit recognition neural network using MATLAB ANFIS kit.
I started by using the MNIST database and I figured out it's almost impossible to classify 784 dimension data using ANFIS. ...
