If you are able to read this, then that means I’ve finally managed to put my small blog online and will publish more interesting posts soon. The goal of this blog is to journal topics I have recently studied using what is sometimes called the Feynman Technique:
- Write down a concept or problem you want to understand.
- Explain the idea as if you had to teach it to someone else.
- Whenever you are confused or there are gaps in your explanation, go back to the source material and understand it better.
The results should be blog posts which are mostly self-contained and explain a specific subject truly well. What I am striving for is quality akin to posts on distill.pub, which are great examples of how complex topics should be illustrated.
As a first example, I wrote a post on loss functions in deep learning. What I started with was a basic understanding of when different functions should be used and the mathematical concept of distance. The result connects these ideas and illustrates the reasons for using them when we do.