1/ ๐ง ๐ค ๐ How to approach a Machine Learning problem?
๐งต A thread
๐
TIPS:
โ Start with the simplest models
โ Identify the patterns from data
โ Let the data speak
โ Don't force data to cry
2/ โ Spend most of your time in EDA, preprocessing, and feature engineering
โ Choose the tech stack with which you are more familiar
โ Try to involve people with domain expertise.
โ Visualize your data. It helps a lot in understanding the patterns.
May 12, 2020 โข 6 tweets โข 5 min read
JAVASCRIPT ON EMBEDDED DEVICES
Case Study: Svelte
(1) - Svelte is used for POS systems in Brazil. Roughly 200,000 POS devices are currently in the cities of Brazil. The device runs a very outdated WebKit on extremely memory-constraint hardware.
@sveltejs@SvelteSociety(2) - They tried different frameworks. None of them could be used because when you press a button, it responded half a second later. Of course, users would be more likely to press it twice and may end up overcharging the customer. But when they tried Svelte, it worked smoothly.