Arushi04/character-level-RNN

This project trains a few thousand names from 18 languages of origin and predicts which language a name is based on the spelling. It uses a character-level LSTM model to predict the next character. The model reads words as a series of characters and outputs a prediction and a “hidden state” at each step, feeding its previous hidden state into each next step. We take the final prediction to be the output, i.e. which class the word belongs to.

Jupyter Notebook