Learn by Source
IBM · on edX

Deep Learning with TensorFlow and Keras

Intermediate 20 hours English Course CertificateFREE
SkillsDeep learningTensorFlowKerasNeural networksPythonModel training

Is this course right for you?

Our take
IBM's edX course covering the same core deep-learning ground as its PyTorch track — neural networks, training, evaluation — but through Google's TensorFlow and the high-level Keras API.

Good for: Learning deep learning with TensorFlow and Keras.

Skip if: You prefer PyTorch, or cannot code Python.

That framework choice is the whole point of picking this over the PyTorch version: take it if your workplace or goals favour TensorFlow, and take the PyTorch track instead if they don't. Either way it's a technical, code-along course that assumes you can already program in Python. Audit it free on edX, with a paid verified certificate and financial assistance available. The concepts transfer even as the frameworks evolve (as of 2026).

Comparison · LBS

Compare alternatives for Deep Learning with TensorFlow and Keras

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.
edX
Deep Learning with TensorFlow and Keras
Price
Free
Audit free · paid verified certificate
Duration
20 hrs
Level
Intermediate
Certificate
Course Certificate
freeCodeCamp4.7(5,800)
Machine Learning with Python Certification
Price
Free
Completely free, forever
Duration
300 hrs
Level
Intermediate
Certificate
Course Certificate
View course →
edX
Deep Learning with Python and PyTorch
Price
Free
Audit free · paid verified certificate
Duration
20 hrs
Level
Intermediate
Certificate
Course Certificate
View course →
DataCamp4.8(53)
Introduction to TensorFlow in Python
Price
Paid
DataCamp subscription
Duration
4 hrs
Level
Intermediate
Certificate
Course Certificate
View course →
Prices & availability can change — confirm on the provider's site. We're not affiliated with any single provider.

About this course

Deep Learning with TensorFlow and Keras covers the same core deep learning ground as IBM's PyTorch track — neural networks, training, evaluation — but through Google's TensorFlow and its high-level Keras API instead. It's the right pick if your team or target job uses TensorFlow specifically, since the two frameworks aren't interchangeable in day-to-day use despite similar underlying concepts.

Browse all AI & ML courses Browse all edX courses

Instructor

I
IBM
edX instructor

Taught by IBM's data science and AI training team.

Frequently asked questions

Both are major deep-learning frameworks. PyTorch dominates research and much of industry now, and many find it easier to learn, so it is often the recommended first choice today. TensorFlow (with Keras) remains widely used in production and is far from obsolete, so learning it is not wasted. If you have a specific job or project in mind, follow what it uses; otherwise either is a reasonable choice, and concepts transfer between them.

Keras is a high-level, user-friendly interface for building neural networks that runs on top of TensorFlow, making it much simpler to define and train models than working with lower-level TensorFlow directly. It is the standard way most people use TensorFlow today, so this course teaching TensorFlow with Keras means you learn deep learning through an accessible, widely-used API rather than raw, verbose code.

Yes. It teaches deep learning with TensorFlow and Keras in Python, so comfortable Python is essential before starting. It also helps to understand basic machine-learning and neural-network concepts, since it focuses on implementing them rather than teaching the theory from scratch. Arriving without Python means wrestling with code instead of learning deep learning, which is the point of the course.

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 and training networks in TensorFlow and Keras, the paid track is worth considering if you want the hands-on practice rather than only the lectures.

It is a focused course — typically a few weeks at a modest weekly pace, faster with solid Python and ML grounding. It is hands-on, so the time goes into building and training deep-learning models with TensorFlow and Keras, with the wider IBM deep-learning path a longer commitment if you continue through its other courses.
Free
to audit
Enroll now