1. Aprender
    2. /
  2. Cursos
    3. /
  3. Recurrent Neural Networks (RNNs) for Language Modeling with Keras
  • 1

    Recurrent Neural Networks and Keras

    Gratuito

    In this chapter, you will learn the foundations of Recurrent Neural Networks (RNN). Starting with some prerequisites, continuing to understanding how information flows through the network and finally seeing how to implement such models with Keras in the sentiment classification task.

  • 2

    RNN Architecture

    You will learn about the vanishing and exploding gradient problems, often occurring in RNNs, and how to deal with them with the GRU and LSTM cells. Furthermore, you'll create embedding layers for language models and revisit the sentiment classification task.

  • 3

    Multi-Class Classification

    Next, in this chapter you will learn how to prepare data for the multi-class classification task, as well as the differences between multi-class classification and binary classification (sentiment analysis). Finally, you will learn how to create models and measure their performance with Keras.

  • 4

    Sequence to Sequence Models

    This chapter introduces you to two applications of RNN models: Text Generation and Neural Machine Translation. You will learn how to prepare the text data to the format needed by the models. The Text Generation model is used for replicating a character's way of speech and will have some fun mimicking Sheldon from The Big Bang Theory. Neural Machine Translation is used for example by Google Translate in a much more complex model. In this chapter, you will create a model that translates Portuguese small phrases into English.

Initializing

Exercicio

Keras models

In this exercise you'll practice using two classes from the keras.models module. You will create one model using the Sequential class and another model with the Model class.

The Sequential class is easier to use because the layers are assumed to be in order, while the Model class is more flexible and allows multiple inputs, multiple outputs and shared layers (shared weights).

The Model class needs to explicitly declare the input layer, while in the Sequential class, this is done with the input_shape parameter.

The objects and modules Sequential, Model, Dense, Input, LSTM and np (numpy) are already loaded on the environment.

Instruções 1/2

undefined XP
  • 1
    • Instantiate theSequential model with name sequential_model.
    • Add one LSTM layer and one Dense layer, and print the summary.
  • 2
    • Create an Input layer, add LSTM and Dense layers and store in main_output.
    • Instantiate the model and print its summary.