Stack Exchange Network

Stack Exchange network consists of 174 Q&A communities including Stack Overflow, the largest, most trusted online community for developers to learn, share their knowledge, and build their careers.

Visit Stack Exchange

Questions tagged [overfitting]

For questions about the over-fitting of data-sets in Machine Learning algorithms.

0
votes
0answers
9 views

Simplified Inception-Resnet for small datasets

I trained a neural network for face recognition with triplet loss using the Inception-Resnet v1 architecture (see figure below, taken form the paper). However, since the dataset is very small compared ...
1
vote
1answer
15 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 ...
2
votes
1answer
31 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 ...
5
votes
1answer
68 views

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

I am training a Multilayer Neural Nets with 146 samples (97 for training set, 20 for validation set and 29 for testing set). I am using: automatic differentiation, SGD method, fixed learning rate + ...
4
votes
1answer
36 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 ...
3
votes
2answers
77 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 ...
1
vote
1answer
45 views

Interpretation of a good overfitting score

As shown below, my deep neural network is overfitting : where the blue lines is the metrics obtained with training set and red lines with validation set Is there anything I can infer from the fact ...
4
votes
1answer
84 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 ...
6
votes
2answers
76 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. ...
1
vote
1answer
78 views

Is this overfitting avoidable?

I am trying a modification of Mobilenet in which I add feedback from the softmax layer into the early layers (to implement this I put a second net after the first, which receives connections from the ...
6
votes
3answers
607 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. ...
9
votes
4answers
520 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?
3
votes
1answer
62 views

What are the methods of optimizing overfitted models?

I'm worrying that my network has become too complex. I don't want to end up with half of the network doing nothing but just take up space and resources. So, what are the techniques for detecting and ...
6
votes
1answer
115 views

What is “early stopping” in relation to AI, and why is it important?

What is "early stopping" and what are the advantages using this method? How does it help exactly? I've read the wiki, but I'd be interested in perspectives, and links to recent research.