Do we need to perform cross validation on googlenet or alexnet

I’ｍ very new to programming.

I am writing the image classification code based on the following tutorial,

https://jp.mathworks.com/help/deeplearning/examples/create-simple-deep-learning-network-for-classification.html

https://jp.mathworks.com/help/deeplearning/examples/train-deep-learning-network-to-classify-new-images.html

In the above tutorial, it seems that they are not using cross validation.

Does it mean that we don't need to use cross validation in the above tutorial?

Or do we have to use cross validation?

Thank you very much in advance!

[CHHAVI]

I have the same query. Have you done cross validation? please explain if you know.

Answer 1

[Anant Upadhyay]

The tutorials mentioned by you(links given in question) provides you with practical examples on how to use Deep Learning networks for classification, and, train deep learning networks to classify images.

The tutorials are meant to guide you on how to use deep learning for your classification problem. The use of cross-validation depends upon the problem statement, dataset and other factors. You should not hold yourself from using cross-validation on your problem statement because the tutorial does not mention it.

Cross-validation is a practical and reliable way for testing the predicting power of methods. It's necessary for any machine learning techniques. Even in neural network you need training set, test set as well as validation set to check over optimization. Also, if you do not have a well separated training and test dataset / or if you are not confident of what percentage of data you should consider for test and training so that there is minimum over fitting or under fitting, cross validation is the best option.

You can find out more about how to use cross-validation in MATLAB from the documentation:

https://www.mathworks.com/help/stats/cvpartition.html

[ssk]

Thanks for your guidance, i decided to use cross validation on my small dataset.