Project: build a two-layer network and check its gradients
Bike rides climb with temperature, then fall when it gets too hot, and no straight line can follow. Build the network that can, from scratch in NumPy, and prove its gradients are right.
Lesson overview
Bike rides climb with temperature, then fall when it gets too hot, and no straight line can follow. Build the network that can, from scratch in NumPy, and prove its gradients are right.
What you’ll explore
- Build a two-layer network by hand, compute its forward pass and gradients, confirm them with a gradient check, and train it with simultaneous updates while reading the loss curve.
Original explanations, connected to the research.
Dive into Deep Learning — authors’ open textbookPrepare a project review
Give someone the context to challenge your thinking.
Download the authored brief, deliverables, and review criteria with your notes. Use the worksheet for self or peer review. Project artifacts are ungraded here, and this review does not award mastery credit.
Suggest a correction
A precise note can make an explanation better.
Choose the scene and describe what needs attention. Download a feedback file to share through a channel you already use. This page does not send feedback or connect you with a reviewer.