Skip to main content

Explore our questions

0 votes
1 answer
201 views

Dimension Mismatch in Transformer Decoder: What Are the Input and Output Dimensions?

3 votes
2 answers
220 views

What are the state of the art optimization methods for neural networks?

0 votes
2 answers
197 views

Rank Neurons Importance of the latent space of an Autoencoder using PCA

0 votes
0 answers
30 views

Independence and Correlation Structure of Weights Generated by a Hypernetwork

3 votes
2 answers
5k views

How to handle even and odd convolutional filter sizes and images

0 votes
0 answers
18 views

Why does batch normalization make lower layers 'useless' in purely linear networks?

0 votes
1 answer
205 views

Accuracy is 100% but model.predict is totaly wrong! what could be the problem? (Autoencoder NN)

2 votes
1 answer
564 views

Sampling from a Convolutional Restricted Boltzmann Machine's Visible Gaussian Real-valued Units

5 votes
1 answer
3k views

Training batch size in relation to number of classes in a neural network

5 votes
1 answer
3k views

Training batch size in relation to number of classes in a neural network

1 vote
1 answer
452 views

Boltzmann machines - unclamped / negative phase

2 votes
1 answer
592 views

How should I formalize Doc2Vec Matrix Dimension?

2 votes
1 answer
531 views

Backpropagation Through Time Error Computation

8 votes
1 answer
3k views

Overfitting a neural network to a single batch as a sanity check - how small a loss value is small enough and long to run for?

Browse more Questions