Deep Learning Essentials

The University of Pennsylvania connects the history of deep learning with perceptrons, optimization and kernel methods. Fully connected networks lead into backpropagation. This is a foundations-focused option for learners who want to understand how network parameters are learned rather than only call a training API.

What you will learn

• Explain a perceptron and a fully connected network.
• Describe stochastic gradient descent as a learning method.
• Trace the role of backpropagation in parameter updates.

Who this suits

Intermediate learners with Python programming experience, as required by the provider.

Before you enroll

Preview the mathematics, coding framework and exercise environment. Compare results on held-out data and investigate failure cases before deciding that a more complex network is useful.

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

Work through one parameter update for a very small network. Compare the calculation with code and explain what the gradient says about the next step.

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.