Skip to main content

Explore our questions

0 votes
0 answers
5 views

Generation of text describing moving objects in video

0 votes
2 answers
834 views

Does it make sense to add an additional attention layer while fine-tuning Bert?

1 vote
1 answer
126 views

Embedding Quality of Transfer Learning model vs Contrastive learning model

0 votes
2 answers
47 views

Classifier-Free-Guidance with Transformers

0 votes
1 answer
67 views

Does Machine Learning focus on discriminative AI while Deep Learning also focus on generative AI?

0 votes
0 answers
10 views

What is the reason for the difference between the expected input tensor order for LSTM and Conv1d?

0 votes
1 answer
47 views

Why does SSIM in pytorch-mssim need the data range to be specified?

0 votes
0 answers
13 views

How to quantify the tone of a textual paragraph? If there is historical communication available, how to check for consistency in tonality for new i/p?

3 votes
1 answer
94 views

What part of the Vaswani et al. is the "transformer"?

0 votes
1 answer
42 views

What is the relation between any suitable measure of model complexity, number of training examples and network size in deep learning?

0 votes
2 answers
174 views

How to encode categorical data for a convolutional model?

0 votes
1 answer
31 views

For given units of a measure of model complexity, how many examples do we need to train a network to get the model right and generalize?

0 votes
1 answer
40 views

High Fluctuations in Validation Curve

5 votes
1 answer
2k views

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

Browse more Questions