Overview

Learn how to use RNNs to classify text sentiment, generate sentences, and translate text between languages.

Learn How to Use RNN Modeling in Python

In this course, you will learn how to use Recurrent Neural Networks to classify text (binary and multiclass), generate phrases, and translate Portuguese sentences into English.

Machine Learning models are based on numerical values to make predictions and classifications, but how can computers deal with text data? With the huge increase of available text data, applications such as automatic document classification, text generation, and neural machine translation are possible. Here, you’ll learn how RNNs in machine learning can help with this process.

Discover the Power of Recurrent Neural Networks

You’ll start this four-hour course by looking at the foundations of Recurrent Neural Networks. Exploring how information flows through a recurrent neural network, you’ll use a Keras RNN model to perform sentiment classification.

As you review RNN architecture in more detail, you’ll learn about vanishing and exploding gradient problems and how to embed layers in a language model.

Explore Language Models With Real-Life Data

Building on this knowledge, you’ll discover how you can prepare data for a multi-class classification task, exploring how these tasks differ from binary classification.

Finally, you’ll learn how to use RNN models for text generation and neural machine translation. You’ll use your knowledge of recurrent neural networks to replicate the speech of Sheldon from The Big Bang Theory and to translate Portuguese phrases into English.

This course provides an in-depth look at RNNs in machine learning, giving you the knowledge to build your skills in this area.

Syllabus

Recurrent Neural Networks and Keras

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.

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.

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.

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.