I recently developed a DNN model and I want to know what exactly is training time and what all steps are included in it? For ex I carried out the following steps:

  1. Determined best Network Architecture by 5 fold CV ( using Back-propagation)
  2. Once I got the Best architecture I used unsupervised learning to get initial weights using unlabled data
  3. I applied back-propagation to fine tune the network with initial weights given by step 2 (It ran for 500 epochs)

What is the training time in this procedure? Does it include all the steps or only steps 2 or 3? Or in general terms does the training time include time to run the code for the best architecture or it also includes the time taken to determine the best network architecture?


(This should be a comment, but don't have enough reputation)

Training time in this case only includes step 2 and 3. Deciding the best network architecture is the essential part of any neural network problem. But after deciding the configurations, you are going to use same network configuration for training and testing. So, taking the time for deciding model configuration into calculation doesn't make sense.

  • $\begingroup$ Why should this be a comment? You pretty much answered the question. $\endgroup$ – Jan Kukacka Mar 22 '18 at 7:20
  • $\begingroup$ Thank you @JanKukacka. I wrote that line because I thought there is nothing much to explain. But happy to know that I answered the question quite well. $\endgroup$ – Sanjay Chandlekar Mar 22 '18 at 7:39

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.