Module 15
Neural Networks 2: Deep Learning in Practice
See how networks train with gradient descent, train an image model on a public dataset, and know the costs and limits of deep learning.
2 lessons + quiz4 hours
Learning Objectives
- 1Explain loss, gradient descent, and learning rate
- 2Train an image classifier on a public dataset and read its training curves
- 3Describe what a convolution filter detects
Lessons
1
Gradient Descent: How Networks Train
Measure how wrong a model is with a loss, then walk downhill one small step at a time.
2
Images and Convolution
How networks see: images as grids of numbers, filters that detect edges, and a digit classifier trained on public data.
Module 15 Quiz: Deep Learning in Practice
Passing score: 80% · 5 questions
Quiz