15 votes
Accepted

Why do you not see dropout layers on reinforcement learning examples?

Dropout essentially introduces a bit more variance. In supervised learning settings, this indeed often helps to reduce overfitting (although I believe there dropout is also already becoming less.. ...
  • 9,659
8 votes
Accepted

What is "early stopping" in machine learning?

In some iterative learning methods the more iterations you apply the more specific your model becomes about the training set. If there are too many iterations, your model will become too specifically ...
  • 381
8 votes
Accepted

What is the "dropout" technique?

Dropout means that every individual data point is only used to fit a random subset of the neurons. This is done to make the neural network more like an ensemble model. That is, just as a random ...
  • 4,222
7 votes

Is overfitting always a bad thing?

Typically the ramification of overfitting is poor performance on unseen data. If you're confident that overfitting on your dataset will not cause problems for situations not described by the dataset, ...
  • 71
6 votes
Accepted

How can the generalization error be estimated?

Generalization error is the error obtained by applying a model to data it has not seen before. So, if you want to measure generalization error, you need to remove a subset from your data and don't ...
  • 2,059
6 votes

Are the shortcomings of neural networks diminishing?

Just to add to what has been said in @MikeWise's brilliant answer, All things equal, deep learning models generally rank supreme when compared to other algorithms as the size of the dataset increases:...
6 votes
Accepted

Are the shortcomings of neural networks diminishing?

Neural Networks have other short comings as well. It takes much longer and far more resources to train a neural network than something like a random forest. So if you need speed of training or are ...
  • 176
6 votes

What is the "dropout" technique?

The original paper1 that proposed neural network dropout is titled: Dropout: A simple way to prevent neural networks from overfitting. That tittle pretty much explains in one sentence what Dropout ...
6 votes

Is it possible for a neural network to be used to compress data?

The auto-encoder (AE) can be used to learn a compressed representation (a vectorised hash value) of each observation in the training dataset, $z$, which can then be used to later retrieve the original ...
  • 36.4k
6 votes

Should I continue training if the neural network attains 100% training accuracy?

First of all, as mentioned by @Neil Slater in the comment - you need to have three splits into the train, validation and test set. One sometimes disregards the difference between validation and test ...
5 votes
Accepted

What is the best measure for detecting overfitting?

tl;dr The safest method I've found is to use cross-validation for hyperparameter selection and a hold-out test set for a final evaluation. Why this isn't working for you... In your case, I suspect you'...
  • 3,133
5 votes
Accepted

Are deep learning models more prone to overfitting than machine learning ones?

Your reasoning isn't wrong. Deep Neural Networks (DNNs) have a much larger capacity than simpler ML algorithms (excluding NNs) and can easily memorize even a very complex dataset and overfit. DNNs, ...
  • 3,133
5 votes
Accepted

Is there an argument against using the (reviewed) predictions of a model as ground truth to further train exactly this model?

Using the (unchecked) predictions of the model as training data is an approach known as "pseudo-labeling". It can help in certain situations, depending on the underlying structure of your ...
  • 278
4 votes

What are the techniques for detecting and preventing overfitting?

Usually you keep track of training loss and validation loss and apply proper regularization technique (such as L1, L2, dropout, DropConnect, etc.). The more interesting technique is to observe your ...
4 votes

How does rotating an image and adding new 'rotated classes' prevent overfitting?

How can data augmentation reduce overfitting? You write that you can already maybe see how data augmentation can help prevent overfitting in general, but it sounds a bit uncertain and it's still ...
  • 9,659
4 votes

Is overfitting always a bad thing?

Is overfitting always a bad thing? The answer is a resounding yes, every time. The reason being that overfitting is the name we use to refer to a situation where your model did very well on the ...
4 votes
Accepted

How can I avoid overfitting when doing parameter tuning?

Yes. Usually you would use cross validation to avoid overfitting during parameter tuning. If your dataset is large enough, and you don't try too many parameter combinations, this will work well, ...
4 votes
Accepted

Is k-fold cross-validation more effective than splitting the dataset into training and test datasets to prevent overfitting?

K-fold cross-validation is probably preferred in terms of completeness and generalization: you ensure that the system has seen the complete dataset for training. However, in deep learning this is ...
4 votes

Is there an argument against using the (reviewed) predictions of a model as ground truth to further train exactly this model?

The answer is: It depends. What you describe is a strategy often used to save time and costs for labelling data. It is important that the data you have already labelled (the 20%) is representative of ...
3 votes
Accepted

How to overcome overfitting to single player styles in reinforcement learning?

Both of the solutions you suggest seem to be built around the intuition that it's good to ensure that there is sufficient variety in the experiences that you provide to your RL algorithm. That ...
  • 9,659
3 votes

What is the "dropout" technique?

There are some great answers here. The simplest explanation I can give for dropout is that it randomly excludes some neurons and their connections from the network, while training, to stop neurons ...
3 votes

Is k-fold cross-validation more effective than splitting the dataset into training and test datasets to prevent overfitting?

Purely in terms of overfitting, and assuming you train both for equal amounts of time, 70/30 is probably better but performance is not going to be very good. Not training on %30 of data will make both ...
  • 880
3 votes

Is running more epochs really a direct cause of overfitting?

The Problem of Overfitting In most cases, when you increase a lot the number of epochs your model finally overfits. This is because your model reaches the point that it does not learn anymore but ...
  • 909
3 votes
Accepted

Is my GRU model under-fitting given this plot of the training and validation loss?

When ever you are buliding a ML Model don't take accuracy seriously(Mistake done by Netflix that cost them alot), you should try to get the hit scores as they will help you to know how many times your ...
3 votes
Accepted

How can I handle overfitting in reinforcement learning problems?

Overfitting refers to a model being stuck in a local minimum while trying to minimise a loss function. In Reinforcement Learning the aim is to learn an optimal policy by maximising or minimising a non-...
3 votes

How can I handle overfitting in reinforcement learning problems?

The accepted answer does not provide a good definition of over-fitting, which actually exists and is a defined concept in reinforcement learning too. For example, the paper Quantifying Generalization ...
  • 36.4k
3 votes
Accepted

What are possible ways to combat overfitting or improve the test accuracy in my case?

There are a few issues you need to address first. Normalise your data. You should try and keep your values for each input in a good range, otherwise you're never going to train anything useful. A ...
  • 1,316
3 votes
Accepted

Can residual connections be beneficial when we have a small training dataset?

Can residual connections be beneficial when we have a small training dataset? The usual rule of data science investigations applies here: Try it, measure the results, then you will know. It is very ...
  • 25.5k
3 votes

What does it mean by overfitting the test set?

Essentially, any data you use to train or develop the model shouldn't be used as test data. In principle, "unseen" data gives a good estimate for the generalisation performance of the model; ...
  • 990
2 votes

What is the "dropout" technique?

I'll try to answer your questions using Geoffrey Hinton's ideas in dropout paper and his Coursera class. What purpose does the "dropout" method serve? Deep neural nets with a large number ...

Only top scored, non community-wiki answers of a minimum length are eligible