Free course · AI and machine learning

Deep Learning with TensorFlow and Keras

This free course teaches deep learning with TensorFlow and Keras on engineering data: when a neural network beats a random forest, building and training Keras models, tf.data pipelines, CNNs for surface defects with augmentation and transfer learning, 1-D CNNs and autoencoders for vibration, Grad-CAM, and export to TensorFlow Lite. It suits UK engineers with some Python, and helps with machine learning engineer and data scientist roles in manufacturing.

Deep Learning with TensorFlow and Keras is a free online intermediate AI and machine learning course with 13 modules, about 27 hours of video lessons. Learning is free; an optional verifiable certificate costs £19 including VAT when you pass the final exam. Last updated 28 October 2026.

See the modules

Free to learn. Verifiable certificate £19 when you pass the final exam (optional, VAT included).

Level
Intermediate
Modules
13
Video
27 hours

Video time only: reading the notes, the quizzes and the final exam take extra time, at your own pace.

Price
Free

Outcome

What you will be able to do

Explain what a network learns and when to use one; pair activations with losses; build, train and regularise Keras models; feed images and signal windows through tf.data; train CNNs and use transfer learning on small datasets; use 1-D CNNs, LSTMs and autoencoders on sensor windows; evaluate with per-class recall and Grad-CAM; export to TensorFlow Lite and measure latency.

  • Say when a neural network beats a random forest, and when it does not
  • Build and train a Keras model with the right loss, early stopping and dropout, and read its curves
  • Feed images from folders and signal windows from streams through a fast tf.data pipeline
  • Train a CNN on surface defects and lift it with augmentation and transfer learning
  • Classify vibration windows with a 1-D CNN and score anomalies with an autoencoder
  • Report per-class recall, explain a prediction with Grad-CAM and export to TensorFlow Lite

Software

Google Colab (its free tier usually offers a GPU runtime when one is available). TensorFlow and Keras are pre-installed.

Hardware

None. A Raspberry Pi is optional for the deployment module.

Syllabus

13 modules

Each module has video lessons, notes and a short quiz. The final exam closes the course.

  1. 1What a neural network is, and why now5 lessons
  2. 2The neuron, activation and loss3 lessons
  3. 3How it learns: gradient descent and backpropagation5 lessons
  4. 4Keras Sequential: your first model3 lessonsLab
  5. 5Training well: dropout, early stopping, imbalance3 lessonsLab
  6. 6Data pipelines: tf.data for images and windows2 lessonsLab
  7. 7Convolutional networks4 lessons
  8. 8Augmentation and transfer learning3 lessons
  9. 9Sequences: 1-D CNNs, RNNs, LSTMs and autoencoders5 lessons
  10. 10Evaluating and explaining a deep model2 lessonsLab
  11. 11Saving, TensorFlow Lite and the edge3 lessons
  12. 12The project: surface defects end to end4 lessons
  13. 13Final assessment0 lessons

How it works

How this course works

  1. Watch the video lessonsOne module at a time, at your own pace.
  2. Take the module quizA short quiz at the end of each module shows what stuck.
  3. Keep your notesWrite in My notes beside each module and ask the trainer if you are stuck.
  4. Practise in the labOptionalTry a task from the module in the EDWartens Lab, in your browser.
  5. Sit the final examPass it once you have been through the modules.
  6. Certificate, if you want oneOptionalPaid, and only after you pass. Anyone can check it online.

EDWartens Lab

Practise this in the EDWartens Lab

Train a model on plant data, move the decision threshold and weigh the cost of errors in the Lab's AI workbench.

Works alongside Deep Learning with TensorFlow and Keras. The Lab is ai for industry practice in your browser: no install, no hardware, free to use. Sign in as a learner and it opens with your account.

AI for industry: Build AI models.

Levels to try with this course

Optional. Skip it whenever you like: it never blocks your progress or your certificate.

Why practise in a lab

Technical work is judged on what you can do: wiring, commissioning, finding a fault. Doing a task yourself teaches more than watching it a second time, and a lab lets you try it safely before you meet real equipment. It does not replace working on real hardware.

  • Practise safely, so a mistake costs nothing.
  • The lab checks your work like a site test, so you know when it is right.
  • Free, in your browser, with nothing to install.

Certificate

An optional certificate when you pass

Learning is free. Pass the final exam and you can have a certificate for £19, including VAT, with a number employers can check online. It records that you completed a free online course; it is not a regulated qualification or a CPD certificate.

  • Your name, the course, its study time and your final exam score
  • A unique certificate number and a QR code to its verification page
  • Issued by Wartens Ltd; add it to your LinkedIn profile in one click
  • Pay now or after you pass: it is issued the moment you pass the final

How the certificate works

Sample certificate for Deep Learning with TensorFlow and Keras

Credits

Who made the lessons

The video lessons belong to their creators. EDWartens wrote the study plan, notes, quizzes and the final exam.

  • codebasics

    the Deep Learning with TensorFlow 2.0, Keras and Python series

  • freeCodeCamp.org

    the TensorFlow 2.0 complete course and the deep-learning crash course

  • Edje Electronics

    running TensorFlow Lite on a Raspberry Pi

  • Connor Shorten

    a lesson in "Evaluating and explaining a deep model"

Jobs

Jobs this course can lead to

The skills in this course are used in AI and machine learning work, for example as a machine learning engineer, a data scientist and a AI engineer. No course can promise a job, and employers also look for experience, so read what live adverts ask for.

Questions

About this course

Last reviewed 28 October 2026.

When does a neural network beat a random forest?
The course answers this directly: neural networks tend to win on raw images and signal windows, while forests are often better on tidy tables of features. You learn to test both against a baseline before choosing.
Do I need a Raspberry Pi or GPU?
No. The course needs no hardware, and a Raspberry Pi is optional for the deployment module. A GPU is not required to follow the lessons. The deployment module shows how a trained model runs on a small edge device.
Is this enough to get a machine learning job in the UK?
Not by itself. It gives you industrial projects to show, but UK employers also look for software, statistics and deployment skills. Use the projects as a portfolio, then check live vacancies for what each employer asks.
What does the Deep Learning with TensorFlow and Keras course cover?
It has 13 modules. The first are “What a neural network is, and why now”, “The neuron, activation and loss”, “How it learns: gradient descent and backpropagation”, “Keras Sequential: your first model” and “Training well: dropout, early stopping, imbalance”, and 8 more follow. Each module has video lessons, notes and a short quiz.
Where does Deep Learning with TensorFlow and Keras start and where does it end?
It starts with “What a neural network is, and why now” and the last module is “Final assessment”. The final exam closes the course, and passing it is what makes the optional £19 certificate available.
How long is Deep Learning with TensorFlow and Keras?
13 modules with 42 lessons, about 27 hours of video lessons. The largest module is “What a neural network is, and why now” with 5 lessons. Video time only: reading the notes, the quizzes and the final exam take extra time, at your own pace.
Can I practise Deep Learning with TensorFlow and Keras in the browser?
Yes. Some modules of Deep Learning with TensorFlow and Keras have a practice level in the EDWartens Lab, marked Lab on the module list, so you can try the ideas in your browser without installing software.
Do I need a GPU?
No. Google Colab's free tier usually offers a GPU when one is available. The type and quota vary, and sessions end. The models in the course are small and train in minutes on one. Set the runtime type to GPU in the first cell of each notebook.
How much maths?
You see gradient descent and backpropagation once, in twenty lines of NumPy, so you know what the framework does. After that Keras does the calculus and you do the engineering. Nothing in the assessments asks for derivatives.
What are the projects?
A surface-defect classifier on 1,200 images — baseline CNN, augmentation and transfer learning compared on one sealed test set with per-class recall, Grad-CAM and a TensorFlow Lite export — and a vibration-window classifier comparing a 1-D CNN with an LSTM, plus an autoencoder anomaly score trained on healthy data only.
Should I do this before or after the OpenCV course?
After, ideally: the OpenCV course teaches you what a convolution filter is by making you tune one by hand, and it shows when classical vision is enough. This course is for when it is not.
Is the course really free?
Yes. Every module, practice task, project and assessment. You create an account so your progress is saved and the assessments can be marked. The certificate is the only paid item, and only if you want it.
What certificate do I get?
An EDWartens Certificate of Completion, issued when you have finished the modules and passed the final assessment (the project is optional practice), with a verification code anyone can check. It is not a vendor credential and is never described as one.
Who made the video lessons?
The creators named in the Credits block at the foot of this page, on their own YouTube channels. EDWartens did not make the videos and the creators are not affiliated with EDWartens. What EDWartens wrote is the study plan, the notes, the practice tasks, the projects and the assessments.

Want a live class and career support?

The Professional Module is five live days of Siemens PLC, HMI and SCADA with an instructor, then career sessions with our engineers and a CPD certificate.

Engineers talking beside an automation test rig, one looking up and smiling