ML 7.8Lesson outlineLesson 7 of 8 in Module 7
Beyond Squared Error: Poisson and Quantile Regression
Choose the loss that matches the target: counts, or a quantile instead of the mean.
Video in production.
Lesson outline: Beyond Squared Error: Poisson and Quantile Regression
In this lesson12 parts
- 01Counting bikes
- 02Two years of eight o'clock
- 03A straight line
- 04A count, and the Poisson distribution
- 05Effects that multiply
- 06The Poisson loss
- 07Fitting it
- 08Measuring it
- 09A range instead of a mean
- 10A spread that changes
- 11Where it misleads
- 12Code, the sealed days, recap, and what comes next
Builds on
This lesson stands on its own. These go deeper into what it uses.
- ML 3.4: Multiple Linear Regression
- 3.6
- 4.4
- 5.5
- 7.2
- Stats 1.2: The CDF, Percentiles and Quantiles
- 4.2 (which defers the Poisson distribution to this video)