When a human looks at a page. He notices the sets of letters are grouped together separated by white space. If the white space was replaced by another character say z, it would be harder to distinguish words.

For a neural network, spaces are "just another character". How can we set up an RNN so it gives special importance to the difference between certain characters like white spaces and letters so that it will train faster? Assume the input is just a sequence of ASCII characters.


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.