Kailegh
  • Member for 3 years, 11 months
  • Last seen more than 1 year ago
Order of normalization / augmentation for image classification
3 votes

You can use both methods, in the vast majority of examples I have seen and worked with the usual order is. Augmentate your data, rotations, zoomings, flips.... Normalize your images based on the ...

View answer
trying to decrease overfitting with regularisation in CNN
1 votes

Steps for overcoming overfitting are the followings: 1. Add more data 2. Use data augmentation 3. Use architectures that generalize well 4. Add regularization 5. Reduce architecture ...

View answer
Training Error decreasing with each epoch
1 votes

I am not very sure about your case, usually I have seen the same problem but in the other direction, you can take a look here: Quora loss drecrease, accuaracy constant Cross validated loss drecrease, ...

View answer
turn off parts of features in a neural network?
1 votes

As far as I know, you cannot do that. First : Obviously setting the mid-term grades to be all 0s would be be a good option No, actually that is a really bad option, neural networks do not ...

View answer
How do machine learning models (e.g. neural networks) get better over time from new data?
Accepted answer
0 votes

If you only want to add more examples you can retrain the machine learning algorithm you had the day before. But if you want to add new features training it from the beginning is needed, you could ...

View answer
How do I convert strings in CSV into integer in Pandas?
Accepted answer
0 votes

You cannot convert your string product names to integers and expect it to work, if you convert it to integers the algorithm you use will expect a linear relationship between these integers, a ...

View answer