3
votes
MNIST with a TWIST, no labels given, only probabilities
By the way you’ve set up the problem, perfect accuracy is impossible, and we must accept that, even if we know a digit to be a $1$, there’s only a $90\%$ chance of being red, and that’s the best we ...
2
votes
Do I need to normalize data before applying L1, L2 norm in ANN
Even if you don't use regularization, it is highly advised that you normalize your data before inputting to a neural network as it'll significantly affect the gradients. So, yes, you should normalize ...
1
vote
Accepted
Neural networks - calculating output manually if $x_1=x_2=0$ . Should this be easy to do?
You are correct, if input data is just zeros, the output of the first layer would be just the biases transformed with the activation function. The next layer would consume as input the output of the ...

Tim♦
- 113k
1
vote
Accepted
Is it possible to deal with datasets of graphs with different number of nodes in graph nural networks?
Is it possible to do this with graph neural networks?
Yes, this is possible using various GNNs architectures, and you usually do not need to set a maximum number or nodes.
For example, Tox21 dataset ...
1
vote
Accepted
References for cross-validation implementations in Pytorch
All the same considerations for cross validation apply for neural networks as for any other type of model. I.e. the usual scikit-learn (or other options for special situations like grouped+stratified ...
1
vote
Concatenation or separate channels for a CNN
I'm answering this purely from a deep learning architecture persepective. There may well be domain-specific reasons why the authors have chosen the architecture described. This review paper: ...
1
vote
Does the attention mechanism (in CNNs) bring additional parameters/weights to learn to the network?
Usually, it does introduce more parameters. The original definition of attention (by Bahdanau et al.) defines attention energies as a single-layer NN computation:
$$e_i = v^T \tanh \left( Wq + Uk_i + ...
1
vote
Can we model visibility between two points in a 3D space using a neural network?
f is a discontious funtion, which is difficult for a neural network to learn.
You can learn a signed distance function, and test whether it's reachable from A to B to decide visibility.
1
vote
What is the origin of the autoencoder neural networks?
Reviving this thread - In "Neurocomputing" by Robert Hecht-Nielsen @ 1990 there is reference to a 1986 paper by Cottrell/Munro/Zipser that outlines use of a neural network that has the ...
Only top scored, non community-wiki answers of a minimum length are eligible
Related Tags
neural-networks × 10999machine-learning × 3789
conv-neural-network × 1193
classification × 680
lstm × 452
regression × 435
tensorflow × 431
recurrent-neural-network × 422
keras × 408
backpropagation × 407
optimization × 399
time-series × 382
python × 356
gradient-descent × 344
autoencoders × 344
loss-functions × 325
natural-language × 279
reinforcement-learning × 264
computer-vision × 264
image-processing × 224
convolution × 180
r × 179
overfitting × 168
regularization × 159
predictive-models × 158