EDIBM · on edX
Deep Learning with Python and PyTorch
Intermediate 20 hours English Course CertificateFREE
SkillsDeep learningPyTorchNeural networksConvolutional networksPythonMachine learning
Is this course right for you?
Our take
The second half of IBM's PyTorch sequence on edX, picking up where PyTorch Basics leaves off to build actual neural networks — convolutional networks, training loops and the rest.
The work is genuinely technical and code-heavy, and it assumes you've done the first course (or have equivalent PyTorch footing) plus Python, so it's the wrong starting point on its own. Take it after the basics and it's a solid build. Auditing is free on edX; the verified certificate is a paid option. What you learn about building networks carries across PyTorch versions (as of 2026).
Comparison · LBS
Compare alternatives for Deep Learning with Python and PyTorch
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.
EDedX
Deep Learning with Python and PyTorch
- Price
- FreeAudit free · paid verified certificate
- Duration
- 20 hrs
- Level
- Intermediate
- Certificate
- Course Certificate
FRfreeCodeCamp4.7(5,800)
Machine Learning with Python Certification
- Price
- FreeCompletely free, forever
- Duration
- 300 hrs
- Level
- Intermediate
- Certificate
- Course Certificate
EDedX
PyTorch Basics for Machine Learning
- Price
- FreeAudit free · paid verified certificate
- Duration
- 15 hrs
- Level
- Beginner
- Certificate
- Course Certificate
GOGoogle4.7(8,500)
Machine Learning Crash Course
- Price
- FreeCompletely free, self-paced
- Duration
- 15 hrs
- Level
- Beginner
- Certificate
Prices & availability can change — confirm on the provider's site. We're not affiliated with any single provider.
About this course
Deep Learning with Python and PyTorch is the second half of IBM's two-course PyTorch sequence, picking up after PyTorch Basics for Machine Learning to build actual neural networks — convolutional networks, training loops, and the practical mechanics of getting a deep learning model to actually learn.
Instructor
I
IBM
edX instructor
Taught by IBM's data science and AI training team, drawing on IBM's enterprise ML curriculum.
Frequently asked questions
It helps. This builds on IBM's PyTorch basics course, going deeper into neural networks and deep learning with PyTorch, so it assumes the foundational tensors-and-training material from that earlier course. You could start here with equivalent PyTorch knowledge from elsewhere, but the sequence is intended, and arriving without those basics makes the deeper material a steeper climb than it needs to be.
Yes. It teaches deep learning with PyTorch in Python, so comfortable Python is essential, and some grasp of machine-learning fundamentals helps since it focuses on building networks rather than teaching theory from scratch. It is not a Python or beginner-ML primer. Arriving with solid Python and the PyTorch basics behind you is the right preparation for this course.
Deeper deep learning with PyTorch: building and training neural networks, working through architectures and techniques beyond the basics, and applying PyTorch to real modelling tasks. It moves from the introductory PyTorch mechanics toward genuinely building deep-learning models, so you finish more capable of implementing networks yourself rather than only understanding the fundamentals.
You can audit it on Coursera (or via edX depending on the listing) to watch the material at no cost, with graded labs and the certificate behind a subscription. Since the value is in actually building the networks in PyTorch, the paid track is worth considering if you want hands-on practice rather than only following the lectures.
It is a focused course — typically a few weeks at a modest weekly pace, faster with solid Python and PyTorch basics. It is hands-on, so the time goes into building and training the models, with the wider IBM deep-learning path a longer commitment if you continue through its other courses.