New answers tagged

0 votes
Accepted

Is this the right approach to preprocessing data for artificial neural-networks?

Here is what I'd do: Whats the right way to ordinal encode data? If there's a natural ordering to the data, which is your case, then it's fine to map the data to a non-decreasing sequence of numbers. ...
user avatar
0 votes

How to represent multi-label colours in one-hot encoding?

Based on my own experience, where I have tried to predict something that varies and is not exact (e.g. water, hot, cold, tepid, not quite so hot etc...) perhaps a dynamic of fuzzy logic could be ...
user avatar
2 votes
Accepted

Normalizing float prices with movements up to a factor of 100

Mathematically speaking when dealing with fat tailed distributions or values that varies in a range of several order of magnitude the most common and simplest solution is to move to logarithmic space. ...
user avatar
0 votes

Why my classification results are correlated with the proportionality of my data?

I see two main issues here: you have really few data you're using a generic MLP What you observe if just overfitting. You multi layer perceptron is just learning to predict the majority class cause ...
user avatar
0 votes

How to normalize multi inputs and single output?

The only reason to use different normalization functions for X1 and X2 I can conceive is to enhance some features in different ways, but there's nothing wrong in using same normalization for both. of ...
user avatar
2 votes

How to represent multi-label colours in one-hot encoding?

If the order of words doesn't matter in the description of the stone, you could use a bag of words model. You don't need the hashing trick because there's likely only a small fixed set of words used ...
user avatar
3 votes
Accepted

Does the term "data augmentation" imply increasing the training dataset?

I'm not familiar with any "authoritative" single definition somewhere, or not sure who used the term first, but I would personally indeed agree with the reviewer you mention. In fact I've ...
user avatar
  • 9,316
1 vote

Does the converted (now square) distorted image of a face affect the accuracy of the calculation of the similarity in FaceNet?

As Neil Slater said it depends on how the model was trained. Now if you go to the FaceNet implementation in TF in github you can see that in the face alignment they do resize without aspect ratio ...
user avatar
  • 998

Top 50 recent answers are included