in Data Handling by
Q:
Why do RNNs work better with text data in Deep learning?

▼ Show 1 Answer

0 votes
by

The main component that differentiates Recurrent Neural Networks (RNN) from the other models is the addition of a loop at each node. This loop brings the recurrence mechanism in RNNs. In a basic Artificial Neural Network (ANN), each input is given the same weight and fed to the network at the same time. So, for a sentence like “I saw the movie and hated it”, it would be difficult to capture the information which associates “it” with the “movie”.

RNN_deep_learning_interview

The addition of a loop is to denote preserving the previous node’s information for the next node, and so on. This is why RNNs are much better for sequential data, and since text data also is sequential in nature, they are an improvement over ANNs.

Learn More with Madanswer

Related questions

0 votes
asked Nov 2, 2020 in Data Handling by AdilsonLima
...