LDA convergence explained by canine pedigree model
10 minute read
13 hours ago
“What happens if our a priori understanding of the distribution of dog breed groups is incorrect? Is my LDA model doomed?
my wife asked.
Welcome back to part 2 of the series. Here I share my journey explaining LDA to my wife. In a previous blog post, we discussed how LDA works and how it can be understood with a dog pedigree model.
This time, we will learn about the iterative fitting process of LDA!
chapter 1 (link):
- How does LDA work?
- How to explain LDA to a non-technical person?
Part 2 (We are here now!):
- How is LDA iteratively improved?
- How does LDA converge?
- Bonus: Get your LDA cheat sheet here!
Part 3:
- When to use LDA and when not to use it?
- How can I use it in Python?
- What are the alternatives and variants of LDA (other than LLM)?
Let’s get started.
If you haven’t read Part 1 of the series yet, I highly recommend you do so first.