About This Site
As a machine learning engineer you can expect to find articles regarding machine learning, deep learning, statistics and general software engineering. However, the main purpose of this site is first and foremost a means for me to consolidate my knowledge. If others find value in these writings, I consider that an added benefit. Furthermore, as I will detail below, I greatly appreciate it when something that I am ignorant about comes to light. Therefore, if you find that any of my posts are unclear or contain misinformation, then it would greatly be appreciated if you get in contact.
During my undergraduate in Physics I was made aware of a learning method called the Feynman method, named after the famous theoretical physicist. The method encourages learning through teaching, i.e. the best way to learn something is to try and teach it to someone. Although Feynman never formally wrote down a “learning method”, the technique has been posthumously ascribed to him due to his reputation for being able to break down complex topics and explain them in simple language, the most notable example of this being the Feynman Lectures in Physics.
“The first principle is that you must not fool yourself, and you are the easiest person to fool.” - Richard Feynman
The efficacy of this approach lies in the fact that you are the easiest person for yourself to fool, i.e. you can quite easily convince yourself that you understand something. It is only when you go on to try and explain something to someone else, who is not so easy to fool, that you realize the holes in your knowledge.
In my experience you need not explain yourself to an actual person to gain the benefits from this approach. Indeed, simply flipping between the teacher / student frame of mind can confer many of the same advantages. In terms of how I implement this, I usually write notes from the perspective of a teacher. When I find myself reaching for this note in the future, after having forgotten some of the context that I wrote the note under, I will take this opportunity to question and evaluate my understanding. If something isn’t clear this is usually a sign that there is a gap in knowledge somewhere.
This approach to learning also closely aligns with Bloom’s taxonomy, which can be seen as ranking system for ones understanding of a topic:
- Remember: Recall facts and basic concepts
- Understand: Explain ideas or concepts
- Apply: Use information in new situations
- Analyze: Draw connections among ideas
- Evaluate: Justify a stand or decision
- Create: Produce new or original work
I believe making personal notes can get you through the first couple of levels. Solving problems and tackling personal projects can help achieve the next few levels. However, true mastery comes from consolidating this knowledge, making novel connections between concepts, and ultimately creating and sharing original work.