Create a Superhero Name Generator with TensorFlow

Offered By
Coursera Project Network
In this Guided Project, you will:

Natural language generation with a deep learning model

Using tokenizer in TensorFlow

Clock2 hours
IntermediateIntermediate
CloudNo download needed
VideoSplit-screen video
Comment DotsEnglish
LaptopDesktop only

In this guided project, we are going to create a neural network and train it on a small dataset of superhero names to learn to generate similar names. The dataset has over 9000 names of superheroes, supervillains and other fictional characters from a number of different comic books, TV shows and movies. Text generation is a common natural language processing task. We will create a character level language model that will predict the next character for a given input sequence. In order to get a new predicted superhero name, we will need to give our model a seed input - this can be a single character or a sequence of characters, and the model will then generate the next character that it predicts should after the input sequence. This character is then added to the seed input to create a new input, which is then used again to generate the next character, and so on. You will need prior programming experience in Python. Some experience with TensorFlow is recommended. This is a practical, hands on guided project for learners who already have theoretical understanding of Neural Networks, Recurrent Neural Networks, and optimization algorithms like gradient descent but want to understand how to use the TensorFlow to start performing natural language processing tasks like text classification or text generation. Note: This course works best for learners who are based in the North America region. We’re currently working on providing the same experience in other regions.

Skills you will develop

Natural Language ProcessingDeep LearningMachine LearningTensorflowNatural Language Generation

Learn step-by-step

In a video that plays in a split-screen with your work area, your instructor will walk you through these steps:

  1. Introduction

  2. Data and Tokenizer

  3. Names and Sequences

  4. Creating Examples

  5. Training and Validation Sets

  6. Creating the Model

  7. Training the Model

  8. Generating Names

How Guided Projects work

Your workspace is a cloud desktop right in your browser, no download required

In a split-screen video, your instructor guides you step-by-step

Frequently asked questions

Frequently Asked Questions

More questions? Visit the Learner Help Center.