Custom Models, Layers, and Loss Functions with TensorFlow

DeepLearning.AI moves beyond standard sequential models through functional APIs and custom loss functions. Custom layers and models provide progressively more control, with callbacks included as additional material. The course suits developers who need to express behavior that a default model configuration cannot capture.

What you will learn

• Use a functional API to define a model.
• Implement a custom layer or loss function.
• Organize a model with explicit customized behavior.

Who this suits

Intermediate learners with calculus, linear algebra, statistics, AI and deep-learning knowledge, plus Python and framework experience, including decorators and context managers.

Before you enroll

Check the TensorFlow and Keras versions used by the notebooks. APIs and model formats can change; reproduce a small example before investing time in a larger project.

Coursera offers paid enrollment or subscription access. Check the enrollment screen for assessment and certificate terms, trials and any financial-aid options. Provider access terms can change; review them before paying.

Put it into practice

Implement one small custom loss and test it on known inputs. Explain how its values differ from a standard loss before using it in training.

Source and review

This overview is based on the provider's published information, checked on 12 October 2026. It is an editorial assessment, not a claim that we completed the resource. Time filters are approximate study ranges; projects and exercises can take longer.

View the curriculum and current access options at Coursera.

How YellowCourse describes and checks learning resources.