Path overview
On this path, you’ll learn all about deep learning, including how to build, train, and evaluate models with the TensorFlow framework.
You’ll then learn how to conduct forecasts on real data by applying sequential neural network models to time series forecasting.
Next, you’ll learn how to use TensorFlow tools and libraries to work on a range of NLP use cases, including text visualization, sentiment analysis models, and more.
Finally, you’ll learn how to apply convolutional neural networks (CNNs) to computer vision tasks so that you can teach computers to see and interpret digital images.
Best of all, you’ll learn by doing — you’ll practice and get feedback directly in the browser. You’ll apply your skills to several guided projects with realistic business scenarios to build your portfolio and prepare for your next interview.
Key skills
- Building and evaluating deep learning regression models using TensorFlow’s Sequential and Functional APIs in Keras
- Implementing a time series forecast model using LSTM and GRU
- Building and evaluating a deep learning sentiment classification model using Transformers.
- Building and training a CNN for image classification tasks
Path outline
Part 1: Deep Learning in TensorFlow [4 courses]
Introduction to Deep Learning in TensorFlow 12h
Objectives- Explain the major concepts and terminology used in deep learning
- Perform data preprocessing and exploratory analysis to prepare data for modeling
- Build and evaluate deep learning regression models using TensorFlow’s Sequential and Functional APIs in Keras
- Build a deep neural network to predict listing gains of IPOs on the Indian market
Sequence Models for Deep Learning 12h
Objectives- Describe sequential neural network models
- Determine when to use RNN, GRU, and LSTM
- Implement a sequential model using a basic RNN
- Implement a time series forecast model using LSTM and GRU
Natural Language Processing for Deep Learning 12h
Objectives- Process and explore text data
- Visualize text data using a word cloud
- Implement tokenization and word embeddings
- Build sequence models
- Build a transformer-based text classification model
Convolutional Neural Networks for Deep Learning 12h
Objectives- Explain the basics of convolutional neural networks (CNNs)
- Build and train a CNN for an image classification task
- Implement regularization techniques
- Fine-tune a CNN model using transfer learning
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
Impress employers by completing a capstone project and certifying it with an expert review.
Projects in this path
Guided Project: Predicting Listing Gains in the Indian IPO Market Using TensorFlow
Build a deep learning model to predict the listing gains of IPOs in the Indian market.
Guided Project: Time-Series Forecasting on the S&P 500
Build, train, and evaluate an LSTM model with a convolutional layer for S&P 500 index (stock) price prediction.
Guided Project: Classifying Disaster-Related Tweets as Real or Fake
Build a deep learning text classification model to predict whether a given tweet is about a real disaster or not.
Guided Project: Detect Pneumonia Using X-Ray Images with CNNs and Transfer Learning
Build and train multiple deep learning models to detect pneumonia in images of chest X-rays.
Grow your career with
Dataquest.


