Skip to main content
Share Your Experience: Take the 2024 Developer Survey

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.

Filter by
Sorted by
Tagged with
20 votes
1 answer
7k views

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 ...
Matt Hamilton's user avatar
14 votes
4 answers
4k views

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's user avatar
  • 10.5k
13 votes
2 answers
823 views

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, ...
user avatar
12 votes
4 answers
6k views

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. ...
ZakC's user avatar
  • 347
10 votes
1 answer
819 views

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 ...
kenorb's user avatar
  • 10.5k
10 votes
5 answers
1k views

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 ...
Nico A's user avatar
  • 201
8 votes
3 answers
10k views

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 ...
Leo's user avatar
  • 133
7 votes
2 answers
6k views

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 ...
malioboro's user avatar
  • 2,819
7 votes
2 answers
799 views

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 ...
thzu's user avatar
  • 73
7 votes
2 answers
760 views

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 ...
AAC's user avatar
  • 171
7 votes
1 answer
439 views

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 ...
GKozinski's user avatar
  • 1,260
7 votes
2 answers
4k views

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 ...
SpiderRico's user avatar
  • 1,000
7 votes
1 answer
2k views

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 ...
Aref.a's user avatar
  • 79
6 votes
4 answers
1k views

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, ...
Bryan Tan's user avatar
  • 183
6 votes
4 answers
1k views

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 ...
jennifer ruurs's user avatar
5 votes
3 answers
10k views

How can the generalization error be estimated?

How would you estimate the generalization error? What are the methods of achieving this?
kenorb's user avatar
  • 10.5k
5 votes
1 answer
796 views

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

In my opinion, deep learning algorithms and models (that is, multi-layer neural networks) are more sensitive to overfitting than machine learning algorithms and models (such as the SVM, random forest, ...
jennifer ruurs's user avatar
5 votes
1 answer
498 views

How can I avoid overfitting when doing parameter tuning?

I very often applied a grid search to tune the parameters of my supervised model. I have the feeling that parameter tuning will eventually (very often) lead to overfitting? Is this crazy to say? Is ...
jennifer ruurs's user avatar
5 votes
1 answer
104 views

What are the techniques for detecting and preventing overfitting?

I'm worrying that my neural network has become too complex. I don't want to end up with half of the neural network doing nothing but just take up space and resources. So, what are the techniques for ...
kenorb's user avatar
  • 10.5k
5 votes
1 answer
193 views

Is running more epochs really a direct cause of overfitting?

I've seen some comments in online articles/tutorials or Stack Overflow questions which suggest that increasing the number of epochs can result in overfitting. But my intuition tells me that there ...
Alexander Soare's user avatar
5 votes
2 answers
8k views

Why did the L1/L2 regularization technique not improve my accuracy?

I am training a multilayer neural network with 146 samples (97 for the training set, 20 for the validation set, and 29 for the testing set). I am using: automatic differentiation, SGD method, fixed ...
LVoltz's user avatar
  • 131
4 votes
2 answers
316 views

How does Regularization Reduce Overfitting?

As I understand, this is the general summary of the Regularization-Overfitting Problem: The classical "Bias-Variance Tradeoff" suggests that complicated models (i.e. models with more ...
stats_noob's user avatar
4 votes
1 answer
110 views

Is there a way to ensure that my model is able to recognize an unseen example?

My question is more theoretical than practical. Let's say that I am training my cat classifier with a dataset that I feel is pretty representative of cat images in general. But then a new breed of cat ...
mdurrant's user avatar
4 votes
0 answers
91 views

Does overfitting imply an upper bound on model size/complexity?

Suppose that I have a model M that overfits a large dataset S such that the test error is 30%. Does that mean that there will always exist a model that is smaller and less complex than M that will ...
Shehryar Malik's user avatar
3 votes
1 answer
326 views

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

I am implementing an actor-critic reinforcement learning algorithm for winning a two player tic-tac-toe like game. The agent is trained against a min-max player and after a number of episodes is able ...
aprospero's user avatar
  • 163
3 votes
1 answer
382 views

When using PCA for dimensionality reduction of the feature vectors to speed up learning, how do I know that I'm not letting the model overfit?

I'm following Andrew Ng's course for Machine Learning and I just don't quite understand the following. Using PCA to speed up learning Using PCA to reduce the number of features, thus lowering the ...
AfiJaabb's user avatar
  • 131
3 votes
1 answer
279 views

Can neural networks learn noise?

I'm interested in the following graphs. A neural network was trained to recognise digits from the MNIST dataset and then the labels were randomly shuffled and the following behaviour was observed. ...
Featherball's user avatar
3 votes
2 answers
146 views

When exactly am I overfitting -- contradicting metrics

I am training an object detection machine learning pipeline. Among the many metrics provided out of the box by tensorflow object detection API, I look at total_loss and DetectionBoxes_Precision/mAP@....
user1091141's user avatar
3 votes
1 answer
133 views

Does adding a model complexity penalty to the loss function allow you to skip cross-validation?

It's my understanding that selecting for small models, i.e. having a multi-objective function where you're optimizing for both model accuracy and simplicity, automatically takes care of the danger of ...
Redrock's user avatar
  • 33
3 votes
1 answer
515 views

Is normalizing the data a way to improve generalization?

There are many known ways to overcome overfitting or make a model generalize better to unseen data. Here I would like to ask if normalizing/standardizing/similiraizing the train and test data is a ...
oezguensi's user avatar
  • 205
3 votes
0 answers
266 views

Does the concept of validation loss apply to training deep Q networks?

In deep learning, the concept of validation loss is to ensure that the model being trained is not currently overfitting the data. Is there a similar concept of overfitting in deep q learning? Given ...
calveeen's user avatar
  • 1,271
3 votes
0 answers
98 views

Are there principled ways of tuning a neural network in case of overfitting and underfitting?

Whenever I tune my neural network, I usually take the common approach of defining some layers with some neurons. If it overfits, I reduce the layers, neurons, add dropout, utilize regularisation. ...
Fasty's user avatar
  • 151
3 votes
0 answers
104 views

How to train CNN such it eliminate dependent features and focuses on independent ones?

How we should train a CNN model when training dataset contains only limited number of cases, and the trained model is supposed to predict class (label) for several other cases, which has not seen ...
2i3r's user avatar
  • 131
2 votes
1 answer
2k views

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

I have a neural network where there are two hidden layers. Each hidden layer has 128 neurons. The input layer has 20 inputs, and the output layer has 3 outputs. I have 1 million records of data. 80% ...
user366312's user avatar
2 votes
1 answer
173 views

Is it a sign of overfitting when validation_loss dips and then goes up with increasingly bigger swings?

I am experimenting with a ConvNet to categorize images taken with a depth camera. So far I have 4 sets of 15 images each. So 4 labels. The original images are 680x880 16-bit grayscale. They are scaled ...
Mike de Klerk's user avatar
2 votes
1 answer
168 views

Am I overfitting my GAN model?

I'm training a DCGAN model on a 320x320 dataset of images and after an hour of training the generator started to generate (on the same latent space noise as during training) images that are identical ...
JingleBells's user avatar
2 votes
2 answers
58 views

Relation between size of parameters and complexity of model with overfitting

I'm reading the book Pattern Recognition and Machine Learning by Bishop, specifically the intro where he covers polynomial regression model. In short, let's say we generate $10$ data points using the ...
Shirish's user avatar
  • 393
2 votes
2 answers
4k views

How to improve testing accuracy when training accuracy is high?

Following-up my question about my over-fitting network My deep neural network is over-fitting : I have tried several things : Simplify the architecture Apply more (and more !) Dropout Data ...
Astariul's user avatar
  • 371
2 votes
1 answer
91 views

Why are large models necessary when we have a limited number of training examples?

In Goodfellow et al. book Deep Learning chapter 12.1.4 they write These large models learn some function $f(x)$, but do so using many more parameters than are necessary for the task. Their size is ...
Borun Chowdhury's user avatar
2 votes
1 answer
366 views

How GoogleNet actually deal with reducing overfitting?

Today I was going through a tutorial of Andrew Ng about Inception network. He said that GoogLeNet's hidden layers are also good in prediction and it had somehow a regularization effect, so it reduces ...
Mahir Mahbub's user avatar
2 votes
1 answer
140 views

Can the addition of dropout in a non-overfitting neural network increase accuracy?

According to Wikipedia Dropout is a regularization technique for reducing overfitting in neural networks My neural network is simple enough and does not overfit. Can the addition of dropout, in a ...
Astariul's user avatar
  • 371
2 votes
0 answers
21 views

2-stage model overfitting

I'm trying to build an entity matching model. There are 2 kinds of features - binary (0/1) and text features. Initially I made a deep learning model that uses character level embeddings of some of the ...
user9343456's user avatar
2 votes
1 answer
643 views

Does a bigger neural network learn "worse" representations than a small neural network when the amount of data isn't enough?

Assume we have a neural network and we want to train it on a classification problem. The hidden layers of the neural network are kind of feature representations of the input data. If the neural ...
realmarv's user avatar
2 votes
2 answers
983 views

Why don't neural networks project the data into higher dimensions first, then reduce the size of each layer thereafter?

Background From my understanding (and following along with this blog post), (deep) neural networks apply transformations to the data such that the data's representation to the next layer (or ...
Kevin's user avatar
  • 133
2 votes
0 answers
336 views

How to prevent deep Q-learning algorithms to overfit?

I have recently solved the Cartpole problem using double deep Q-learning. When I saw how the agent was doing, it used to go right every time, never left, and it did similar actions all the time. Did ...
dato nefaridze's user avatar
2 votes
0 answers
44 views

Why is the loss of one of the outputs of a model with multiple outputs increasing while the others are decreasing?

I'm a newbie in neural networks. I'm trying to fit my neural network that has 3 different outputs: semantic segmentation, box mask and box coordinates. When my model is training, the loss of ...
João Castilho's user avatar
2 votes
0 answers
125 views

Overfitted model performs better in test set

There are two models for the same task: model_1: 98% accuracy on training set, 54% accuracy on test set. model_2: 48% accuracy on training set, 47% accuracy on test set. From the statistics above we ...
torayeff's user avatar
  • 121
2 votes
2 answers
583 views

Unable to overfit using MLP

I'm building a 5-class classifier with a private dataset. Each data sample has 67 features and there are about 40000 samples. Samples of a particular class were duplicated to overcome class imbalance ...
Ashwin Kannan's user avatar
1 vote
2 answers
991 views

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

I was running my gated recurrent unit (GRU) model. I wanted to get an opinion if my loss and validation loss graph is good or not, since I'm new to this and don't really know if that is considered ...
AliY's user avatar
  • 123
1 vote
1 answer
143 views

How does deep learning overcome overfitting?

From Berkeley CS182, SP22: https://cs182sp22.github.io/assets/lecture_slides/2022.01.26-ml-review-pt2.pdf. Can someone help me interpret this diagram? I understand the graph on the left, but I don't ...
9j09jf02jsd's user avatar