Custom Models, Layers, and Loss Functions with TensorFlow
DeepLearning.AI · View on Coursera ↗
Taught by Laurence Moroney, Eddy Shyu
Data ScienceComputer Science
About the course
In this course, you will: • Compare Functional and Sequential APIs, discover new models you can build with the Functional API, and build a model that produces multiple outputs including a Siamese network. • Build custom loss functions (including the contrastive loss function used in a Siamese network) in order to measure how well a model is doing and help your neural network learn from training data. • Build off of existing standard layers to create custom layers for your models, customize a n
The dissent
The most-upvoted critical review (20 votes, 2.0★).
“The course is basically a presentation of semi-digested Keras tutorials, sometimes outdated. No depth and no real-world experience were communicated. The notebooks are mediocre, lazy and minimalistic, here-they-work-here-they-don't. You will not use them for your portfolio. I wouldn't call this course "advanced", it's rather a shallow overview of advanced techniques.”
Coursera's 4.9 comes from 1,111 ratings. Of those, 0.7% 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 22 Oct 2026.Read them on Coursera ↗