Last week I made a massive 4000 words article about mathematics the No. 1 trending on Medium.
I achieved this by setting three guiding principles, resulting in explosive growth.
Here is a thread about how can you do it too.
1⃣ Set out to write the single most important article on the topic. Instead of looking for quick wins, aim to create the best resource out there.
Making this article took me more than a month. Every minute of work was worth it.
Pay attention to all the details, make sure you understand every nook and cranny of the subject.
Explain complex technical details in a way such that even newcomers would get them.
Never compromise on quality. If you think that something can be done better, do it.
2⃣ Don't create content with an expiration date. No one will read your "3 Awesome Features of PyTorch 1.7" article after 1.8 comes out. No one will read your "10 Best Books on Data Science To Read in 2020" in the following years.
Write pieces people would revisit over and over.
Have you read the book Deep Learning by @goodfellow_ian, Yoshua Bengio, and Aaron Courville? A timeless classic, one of the most cited textbooks.
Strive to be like that in an article format.
Good examples to follow:
📰 Object Detection for Dummies series by @lilianweng.
They are three and six years old, respectively, but I still revisit them occasionally — impressive writing quality, combined with an exciting and timeless topic.
Work hard to make every article of yours like this.
3⃣ Create a beautifully designed visualization and jam-pack it with knowledge.
What would you rather click on? A block of text from an interesting topic or a stunning graphics? Most people are visual, and it is easier to facilitate engagement with images than with words.
The one in my viral post was shared more times than I dare to count. Visuals made people click, content made them stay.
If you don’t have any visual skills, hire a graphical designer on Upwork or Fiverr to turn your sketch into a captivating illustration. (As I did here.)
In case you don't know how, learn from @neilpatel.
Have you ever implemented a dynamic function dispatcher in Python, where you can register functions at runtime using the decorator syntax? (Like the routers for FastAPI.)
I did this recently, and I am going to teach you how to do it! I'll walk you through it in the thread below.
We will build an event handler to catch arbitrary events and dynamically execute a function to handle the event.
(A good example is catching events in a webhook listener.)
Time to use some decorator magic!
The usage is straightforward: 1) instantiate the EventHandler, 2) register handler functions for specific events, 3) pass the event to the EventHandler instance when caught.
Neural networks are getting HUGE. In their @stateofaireport 2020, @NathanBenaich and @soundboy visualized how the number of parameters grew for breakthrough architectures. The result below is staggering.
What can you do to compress neural networks?
👇A thread.
1⃣ Neural network pruning: iteratively removing connections after training. Turns out that in some cases, 90%+ of the weights can be removed without noticeable performance loss.
A few selected milestone papers:
📰Optimal Brain Damage by @ylecun, John S. Denker, and @SaraASolla. As far as I know, this was the one where the idea was introduced.
1️⃣ If you struggle to understand determinants, stop what you are doing and check out this video by @3blue1brown, it will make your brain explode.
2⃣ Sometimes, it is hard to figure out what a concept represents by looking at how it is calculated. The determinant of a matrix is calculated by a sum, iterating through all permutations of a row.
3⃣ However, this definition doesn't reveal anything about what the determinant means. In fact, it is quite simple: it describes how the volume scales under the corresponding linear transformation.