Now that we're at the end of the chapter, let's see what we've learned. To finish this chapter, I've included three exercises that will challenge you based on what we've covered in this chapter:
- Add an extra layer to the encoder of the translation model. The translation model might work better if it had a bit more capacity to learn the structure of French sentences. Adding one more LSTM layer will be a good exercise to learn about the functional API.
- Add attention to the encoder of the translation model. Attention will allow the model to focus on the (English) words that really matter for translation. It is best to use attention as the last layer. This task is a bit harder than the previous one, but you will understand the inner workings of attention much better.
- Visit Daily News for Stock Market Prediction at https://www.kaggle.com/aaron7sun/stocknews. The task is to use the daily news as an input to predict stock prices. There are a number of kernels already that can help you with this. Use what you have learned in this chapter to predict some stock prices!
..................Content has been hidden....................
You can't read the all page of ebook, please click here login for view all page.