this is my first post here so please point me in the right direction if the question isn't appropriate.

I am interested in learning more about 'online' or 'continuous learning' neural networks - that is, an algorithm that learns from a single example at a time and then moves onto the next, rather than one which iterates over an entire training set. Most of the courses I've found don't mention them or just briefly touch upon them, but I'm interested in learning about their implementation so I need more detail.

Does anyone know of any good resources (ideally online courses, but also books or websites) to study this type of neural network?

Thanks for your help!


  • $\begingroup$ That's not a type of network in itself. Just a type of usage. However, continuous timeseries and sequences are typically modeled with recurrent neural networks. It's easy to find reading material about that. $\endgroup$ – runDOSrun Jun 9 '15 at 8:10

Your Answer

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

Browse other questions tagged or ask your own question.