Artificial Intelligence Stack Exchange
Artificial Intelligence Stack Exchange

Questions tagged [overfitting]

For questions related to the concept of overfitting in machine learning, which can be loosely defined as the gap between the performance on the training set and the performance on the test set.

98 questions
16
votes
1 answer

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

I've been looking at reinforcement learning, and specifically playing around with creating my own environments to use with the OpenAI Gym AI. I am using agents from the stable_baselines project to test with it. One thing I've noticed in virtually…
Matt Hamilton
  • 293
  • 2
  • 5
13
votes
4 answers

What is the "dropout" technique?

What purpose does the "dropout" method serve and how does it improve the overall performance of the neural network?
kenorb
  • 10,423
  • 3
  • 43
  • 91
13
votes
2 answers

Are the shortcomings of neural networks diminishing?

Having worked with neural networks for about half a year, I have experienced first-hand what are often claimed as their main disadvantages, i.e. overfitting and getting stuck in local minima. However, through hyperparameter optimization and some…
user4747
12
votes
4 answers

Is overfitting always a bad thing?

DNN can be used to recognize pictures. Great. For that usage, it's better if they are somewhat flexible so as to recognize as cats even cats that are not on the pictures on which they trained (i.e. avoid overfitting). Agreed. But when one uses NN as…
ZakC
  • 347
  • 2
  • 7
10
votes
4 answers

Why can neural networks generalize at all?

Neural networks are incredibly good at learning functions. We know by the universal approximation theorem that, theoretically, they can take the form of almost any function - and in practice, they seem particularly apt at learning the right…
Nico A
  • 201
  • 2
  • 7
9
votes
1 answer

What is "early stopping" in machine learning?

What is early stopping in machine learning and, in general, artificial intelligence? What are the advantages of using this method? How does it help exactly? I'd be interested in perspectives and links to recent research.
kenorb
  • 10,423
  • 3
  • 43
  • 91
7
votes
2 answers

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

From Meta-Learning with Memory-Augmented Neural Networks in section 4.1: To reduce the risk of overfitting, we performed data augmentation by randomly translating and rotating character images. We also created new classes through 90◦, 180◦ and 270◦…
AAC
  • 171
  • 1
  • 2
7
votes
1 answer

How come that the addition of features can decrease the performance of a neural network?

I have a Remaining Useful Life (RUL) prediction problem that I want to solve. When I added two or more features as inputs to my ANN, the accuracy of my ANN has been decreased. More precisely, I've added features like RMS or KURTOSIS (or both). I was…
Aref.a
  • 79
  • 3
7
votes
2 answers

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

I plan to use my predictions as ground truth to continue training my model. These predictions are of course reviewed during this process. Is there an argument against that (reinforcement of slight mistakes/overfitting etc.)? Here my specific use…
thzu
  • 73
  • 4
7
votes
3 answers

How should we regularize an LSTM model?

There are five parameters from an LSTM layer for regularization if I am correct. To deal with overfitting, I would start with reducing the layers reducing the hidden units Applying dropout or regularizers. There are kernel_regularizer,…
Leo
  • 123
  • 1
  • 6
7
votes
2 answers

Should I prefer the model with the lowest validation loss or the highest validation accuracy to deploy?

I trained a ResNet20 on Cifar10 and obtained the following learning curves. From the figures, I see at epoch 52, my validation loss is 0.323 (the lowest), and my validation accuracy is 89.7%. On the other hand, at the end of the training (epoch…
SpiderRico
  • 960
  • 8
  • 18
7
votes
1 answer

What is the best measure for detecting overfitting?

I wanted to ask about the methodology of testing the ML models against overfitting. Please note that I don't mean any overfitting reducing methods like regularisation, just a measure to judge whether a model has overfitting problems. I am currently…
GKozinski
  • 1,240
  • 8
  • 19
6
votes
2 answers

How can I handle overfitting in reinforcement learning problems?

So this is my current result (loss and score per episode) of my RL model in a simple two players game: I use DQN with CNN as a policy and target networks. I train my model using Adam optimizer and calculate the loss using Smooth L1 Loss. In a…
malioboro
  • 2,729
  • 3
  • 20
  • 46
6
votes
4 answers

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

I want to prevent my model from overfitting. I think that k-fold cross-validation (because it is doing this each time with different datasets) may be more effective than splitting the dataset into training and test datasets to prevent overfitting,…
jennifer ruurs
  • 579
  • 2
  • 8
6
votes
4 answers

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

When training a neural network, we often run into the issue of overfitting. However, is it possible to put overfitting to use? Basically, my idea is, instead of storing a large dataset in a database, you can just train a neural network on the entire…
Bryan Tan
  • 183
  • 7
1
2 3 4 5 6 7