Course overview
In this course, you’ll learn the basics of neural networks, including graph representation, activation functions, multiple hidden layers, and image classification.
You’ll learn the different kinds of nonlinear activation functions, such as the ReLU function, hyperbolic tangent function, and others, to discover how they enable neural networks to capture nonlinearity. You’ll also learn how to add hidden layers — and how they can make neural networks more powerful.
At the end of the course, you’ll complete a project in which you will build a neural network to classify images of digits in the MNIST dataset — and tweak your neural networks for better handwriting recognition. This project is a chance for you to combine the skills you learned in this course and practice building neural networks using a typical deep learning workflow. This project can also serve as a portfolio project that you can show to future employers.
Key skills
- Understanding the representation of neural networks
- Demonstrating how adding hidden layers can improve model performance
- Capturing nonlinearity in the data in neural networks
Course outline
Introduction to Deep Learning [4 lessons]
Representing Neural Networks 2h
Lesson Objectives- Visually represent neural networks
- Implement linear and logistic regression as neural networks
- Identify the differences between the nonlinear activation functions
Nonlinear Activation Functions 1h
Lesson Objectives- Define the different types of nonlinear activation functions
- Improve neural network models with nonlinear activation functions
Hidden Layers 1h
Lesson Objectives- Add hidden layers to make neural networks more powerful
- Train neural networks in scikit-learn
Guided Project: Building A Handwritten Digits Classifier 1h
Lesson Objectives- Define the concepts behind image classification
- Compare different image classification models
- Improve neural networks' handwriting recognition
Projects in this course
Guided Project: Building A Handwritten Digits Classifier
Learn the basics of image classification to build a handwriting classifier.
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.
Learning resources
Grow your career with
Dataquest.


