So I found something strange once I compared the accuracy of the prediction of a class for a question between a CNN and an RNN (GRU).

The CNN achieved 0.87 accuracy over the RNN (GRU) with 0.7520 accuracy. In terms of question classification task, would it makes sense if CNN outperforms RNN or is it a rare case?


CNN considers only the current input while RNN considers the current input and also the previously received inputs. It can memorize previous inputs due to its internal memory

Here's a comparative study on RNN vs CNN on different problems.

Comparative Study

As you can see RNN-GRU outperforms CNN on most of the cases


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.