Generative Deep Learning with TensorFlow
DeepLearning.AI · View on Coursera ↗
Taught by Laurence Moroney, Eddy Shyu
Data ScienceComputer Science
About the course
In this course, you will: a) Learn neural style transfer using transfer learning: extract the content of an image (eg. swan), and the style of a painting (eg. cubist or impressionist), and combine the content and style into a new image. b) Build simple AutoEncoders on the familiar MNIST dataset, and more complex deep and convolutional architectures on the Fashion MNIST dataset, understand the difference in results of the DNN and CNN AutoEncoder models, identify ways to de-noise noisy images, a
The dissent
The most-upvoted critical review (2 votes, 3.0★).
“The session on VAE's was interesting, If I could make a suggestion, I would add other generative models, such as Deep Belief Nets, and show how the generated data change from DBNs to VAES to GANS with the same dataset. That would give students a better idea of the tradeoffs involved in each of them.”
Coursera's 4.8 comes from 317 ratings. Of those, 0.6% are 1–2★.
Starisk reads the reviews learners voted most helpful, and weights each by the square root of its votes: a review with 80 upvotes counts about five times one with 2. Unvoted reviews are not skipped out of laziness — by this model they carry no evidence that other students endorsed them.
That measures what the most-endorsed reviews say, not “true quality.” The rating distribution above is the whole population, so you can see the sample next to it.
Reviews read on 23 Oct 2026.Read them on Coursera ↗