Deep Learning with TensorFlow and Keras

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.

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.

There are two projects. The first is a surface-defect classifier on 1,200 images. You compare a baseline CNN, augmentation and transfer learning on one sealed test set. You use per-class recall and Grad-CAM, and export to TensorFlow Lite. The second is a vibration-window classifier comparing a 1-D CNN with an LSTM. It adds an autoencoder anomaly score trained on healthy data only.

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.

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.

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.

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.

No. The lab is optional practice. You can skip it whenever you like, and it never blocks your progress, the final assessment or your certificate.

Yes. Every lab level for this course opens in your browser, free, with nothing to install.

The Deep Learning with TensorFlow and Keras course has 13 modules. It opens with "What a neural network is, and why now", goes through "The neuron, activation and loss", "Training well: dropout, early stopping, imbalance", "Sequences: 1-D CNNs, RNNs, LSTMs and autoencoders" and "The project: surface defects end to end" and ends with "Final assessment". The full list with minutes is under "What you learn" on this page.

After the Deep Learning with TensorFlow and Keras course: 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. These are the practical outcomes the course is written around, and the final assessment of 15 questions checks them.

For the Deep Learning with TensorFlow and Keras course, 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. The course itself is free.

Deep Learning with TensorFlow and Keras is rated intermediate. Intermediate. Needs the Machine Learning with Python course, or equivalent: train/test discipline, metrics, Pandas. It is written for engineers, developers and students applying AI to real work, and takes about 27.4 hours at your own pace.

Skills from the Deep Learning with TensorFlow and Keras course (for example: say when a neural network beats a random forest, and when it does not) are used in roles such as AI engineer, machine learning engineer, data analyst and automation developer, and in machine learning engineer work. The course gives you practical evidence of the skill; it does not promise a job, and employers decide on experience and interview.