What’s is the difference between train, validation and test set, in neural networks?

by

The training and validation sets are used during training.

for each epoch
    for each training data instance
        propagate error through the network
        adjust the weights
        calculate the accuracy over training data
    for each validation data instance
        calculate the accuracy over the validation data
    if the threshold validation accuracy is met
        exit training
    else
        continue training

Once you’re finished training, then you run against your testing set and verify that the accuracy is sufficient.

Training Set: this data set is used to adjust the weights on the neural network.

Validation Set: this data set is used to minimize overfitting. You’re not adjusting the weights of the network with this data set, you’re just verifying that any increase in accuracy over the training data set actually yields an increase in accuracy over a data set that has not been shown to the network before, or at least the network hasn’t trained on it (i.e. validation data set). If the accuracy over the training data set increases, but the accuracy over the validation data set stays the same or decreases, then you’re overfitting your neural network and you should stop training.

Testing Set: this data set is used only for testing the final solution in order to confirm the actual predictive power of the network.

More Related Contents:

  1. Is this possible to predict the lottery numbers (not the most accurate)? [closed]
  2. developing a learning system using neuro network [closed]
  3. Artificial Neural Network Toplogy
  4. What is the role of the bias in neural networks? [closed]
  5. Clarification on a Neural Net that plays Snake
  6. Epoch vs Iteration when training neural networks [closed]
  7. Why should weights of Neural Networks be initialized to random numbers? [closed]
  8. Neural network XOR gate not learning
  9. Is there any standard rule for considering the best result or at which stage I have to stop train the data with minimum error
  10. Is it possible for a computer to “learn” a regular expression by user-provided examples?
  11. How can I split a text into sentences using the Stanford parser?
  12. What is `weight_decay` meta parameter in Caffe?
  13. Neural network in MATLAB
  14. How do I load a caffe model and convert to a numpy array?
  15. Why must a nonlinear activation function be used in a backpropagation neural network? [closed]
  16. How to recognize rectangles in this image?
  17. How to feed caffe multi label data in HDF5 format?
  18. caffe data layer example step by step
  19. How do I check if keras is using gpu version of tensorflow?
  20. Pytorch, what are the gradient arguments
  21. Caffe: What can I do if only a small batch fits into memory?
  22. Tensorflow : Memory leak even while closing Session?
  23. What is the difference between supervised learning and unsupervised learning? [closed]
  24. keras: how to save the training history attribute of the history object
  25. What is the difference between graph search and tree search?
  26. Using pre-trained word2vec with LSTM for word generation
  27. Can I send callbacks to a KerasClassifier?
  28. Error in Confusion Matrix : the data and reference factors must have the same number of levels
  29. how to implement custom metric in keras?
  30. Choosing number of Steps per Epoch

Leave a Comment