zipline86's user avatar
zipline86's user avatar
zipline86's user avatar
zipline86
  • Member for 4 years
  • Last seen more than a month ago
  • Sweden
4 votes
2 answers
7k views

normalizing data and avoiding dividing by zero

3 votes
1 answer
77 views

Understanding pseudocode for co-democratic learning

3 votes
1 answer
1k views

NLP: what are the advantages of using a subword tokenizer as opposed to the standard word tokenizer?

3 votes
1 answer
2k views

Is a multi-layer perceptron exactly the same as a simple fully connected neural network?

2 votes
1 answer
1k views

How to interpret skimage orientation to straighten images?

2 votes
1 answer
495 views

Production: TensorFlow and Keras

1 vote
1 answer
3k views

Scipy curve_fit and method "dogbox"

1 vote
1 answer
34 views

Understanding math notation in infoGAN paper

0 votes
0 answers
16 views

using logsumexp in softmax

0 votes
1 answer
36 views

Is it common to add noise to Time Series data before training a model

0 votes
1 answer
639 views

Embedding layer before LSTM layer

0 votes
1 answer
100 views

Is epsilon error a standard known error or custom created by this paper?

0 votes
1 answer
116 views

Does anybody know where this rule of thumb came from? Rule of them: embedding vector dimension should be the 4th root of the number of categories