The first course in Andrew Ng's celebrated Deep Learning Specialization on Coursera, and where many people's real understanding of neural networks begins. Rather than hand you a library, it walks through the mechanics — forward and back propagation, and building a network step by step in Python. Excellent teaching, though it expects some maths and coding comfort.
Good for: Genuinely understanding how neural networks work, from a renowned teacher.
Less suitable if: You want a no-maths overview or a plug-and-play library tutorial.
You want to understand neural nets from the ground up
You are comfortable with some maths and Python
You want a rigorous, respected foundation
Consider something else if you…
You want a maths-free overview
You just want to use a library without the theory
You are not yet comfortable with basic programming
Requirements: Basic Python and some comfort with linear algebra and calculus.
Realistic time: Around 20–25 hours over a few weeks.
About this course
Neural Networks and Deep Learning is the first course in Andrew Ng's celebrated Deep Learning Specialization, and it's where most people's real understanding of neural nets begins. Rather than hand you a library, it walks you through the mechanics — forward and backward propagation, activation functions, gradient descent — until you can implement a network in Python yourself.
What you'll learn
Understand how a neural network makes a prediction (forward propagation)
Implement backpropagation and gradient descent from scratch
Choose and reason about activation functions
Build and train a deep network in Python and NumPy
Vectorise computations for efficiency
Develop the intuition to debug why a network isn't learning
This course includes
Yes
Certificate
Yes
Mobile access
English
Language
What it costs
You can audit the course free on Coursera. A certificate needs a Coursera subscription (about $49/month) or Coursera Plus, with financial aid available. It is the first of five courses in the Deep Learning Specialisation.
Comparison · LBS
Compare alternatives for Neural Networks and Deep Learning
Same topic, different options. We surface the trade-offs others hide so you can pick the course that actually fits your time, budget, and goals.
A DeepLearning.AI certificate on Coursera is well respected in the ML community as evidence of the work, though it is a course certificate rather than a formal qualification.
Last updated
Instructor
AN
Andrew Ng
Coursera instructor
Andrew Ng — co-founder of Coursera and DeepLearning.AI, founder of Google Brain — is widely regarded as the most effective teacher in the field. His deep-learning courses are the ones practitioners most often name as the foundation of their understanding.