Course overview
First, you’ll explore the concepts and terms necessary for working with sequential models in TensorFlow. You’ll discover recurrent neural networks (RNN) and how they compare with convolutional neural networks (CNNs), as well as some of the most common RNN applications.
Then, you’ll learn how to build, train, evaluate, and improve a basic RNN to predict song popularity using regression. You’ll also learn to use Gated Recurrent Units (GRU) and Long Short-Term Memory (LSTM) techniques to improve model performance. You’ll implement these to predict the sentiment of the review (good or bad) on a dataset of IMDB reviews.
Next, you’ll combine convolutional neural networks with sequential models to add a convolutional layer to your LSTM model and compare its predictive performance before and after on a dataset of IMDB reviews, predicting sentiment.
Finally, you’ll optimize the tools already used for time-series forecasting on a dataset of movie ticket sales to prepare you for the guided project.
Best of all, you’ll learn by doing – you’ll practice and get feedback directly in the browser. At the end of the course, you’ll apply your new skills to a project to build a model to better forecast how the S&P 500 futures index will move based on its behavior over the past several years.
Key skills
- Processing and exploring text data
- Visualizing text data using a word cloud
- Implementing tokenization and word embeddings
- Building sequence models
- Building a transformer-based text classification model
Course outline
Natural Language Processing for Deep Learning [6 lessons]
Introduction to Natural Language Processing 2h
Lesson Objectives- Differentiate between text and non-text data
- Explore the built-in datasets in the TensorFlow Datasets library
- Prepare text data for analysis
- Create a word cloud on text corpus
Text Vectorizer and Word Embeddings 2h
Lesson Objectives- Use the TextVectorizationxa0layer in TensorFlow for text transformation
- Use and vary parameters needed for building the vectorizer layer
- Perform word embedding using an embedding layer
- Build, train, and evaluate a shallow neural network text classification model
Building Multi-layer (dense) Text Classification Models with TensorFlow 2h
Lesson Objectives- Build a multilayer deep learning text classification model
- Initialize a GlobalAveragePooling1D layer to train a text classification model
- Tune hyperparameters and compare the performance of the model using different architectures
- Implement regularization techniques to mitigate overfitting
Building Sequence Models with TensorFlow 2h
Lesson Objectives- Build a single-layer LSTM deep learning text model
- Build a multilayer LSTM deep learning text model
- Tune hyperparameters for LSTM models
Building Text Models with Transformers 2h
Lesson Objectives- Prepare data for a transformer model
- Perform tokenization using AutoTokenizer
- Build and train a transformer model
- Evaluate the effectiveness of a transformer text classification model
Guided Project: Classifying Disaster-Related Tweets as Real or Fake 2h
Lesson Objectives- Explore and Process text data
- Visualize text data using a word cloud
- Build text classification model using tokenizer and embedding layer
- Build sequence models
- Build a transformer-based text classification model
Projects in this course
Classifying Disaster-Related Tweets as Real or Fake
For this project, you’ll be a data scientist at a news company building a deep learning model to predict if tweets are about real disasters or not. Using a Kaggle dataset, you’ll apply Python, TensorFlow, and NLP to gain in-demand skills.
The Dataquest guarantee
Dataquest has helped thousands of people start new careers in data. If you put in the work and follow our path, you’ll master data skills and grow your career.
We believe so strongly in our paths that we offer a full satisfaction guarantee. If you complete a career path on Dataquest and aren’t satisfied with your outcome, we’ll give you a refund.
Master skills faster with Dataquest
Go from zero to job-ready
Learn exactly what you need to achieve your goal. Don’t waste time on unrelated lessons.
Build your project portfolio
Build confidence with our in-depth projects, and show off your data skills.
Challenge yourself with exercises
Work with real data from day one with interactive lessons and hands-on exercises.
Showcase your path certification
Share the evidence of your hard work with your network and potential employers.
Grow your career with
Dataquest.


