Explore our questions

1 vote
1 answer
10 views

Is it possible to use Mini-Batches with Adam optimization?

1 vote
2 answers
838 views

Why the cost/loss starts to increase for some iterations during the training phase?

0 votes
0 answers
15 views

Validating bundles of XMLs with inconsistent structure

0 votes
2 answers
139 views

In the paper "LLM in a flash," what is meant by an up projection or down projection layer?

0 votes
1 answer
180 views

Dummy variable trap in neural networks and class visualization

0 votes
0 answers
10 views

Predicition of future batches in time series

0 votes
1 answer
48 views

How do I know that my dataset is good enough for training a neural network?

2 votes
1 answer
43 views

What are these special "AI chips" actually used for?

0 votes
0 answers
13 views

19 characters to one prediction

1 vote
0 answers
25 views

What is the best way to train a neural network with a variable number of inputs?

5 votes
1 answer
2k views

Which other loss functions for hierarchical multi-label classification could I use?

1 vote
1 answer
169 views

Reference request: one-hot encoding outperforming random orthogonal encoding

1 vote
1 answer
47 views

NN Architecture for the detection of "sparse" Objects

4 votes
3 answers
119 views

In the VAE, why is $z \sim \mathcal{N}(\mu, \sigma^2)$ equivalent to $z = \mu + \sigma \odot \epsilon$?

Browse more Questions