Digital Materials
Objectives
After this experience, students will be able to
- Describe the data used in facial recognition mathematically.
- Describe multiple ways that image data can be compared, and the affordances/limitations of their methods.
- Explain the role of statistical error in facial recognition.
Questions explored
- How can we compare two faces using numbers?
- How do machines consider the question, “Are these two pictures of the same person?” differently from humans?
- Which method, pixel brightness or face distances, is more reliable and why?
- Why do misclassifications occur, even with “good” models? What are some consequences of misclassified images?
Key Terms
Machine Learning
- When computers learn and get better at a task by using data instead of being programmed with explicit rules on how to do that task.
Model
- A mathematical framework that can be used in AI to make predictions or decisions. Models are often trained with large amounts of data