Embeddings are one of the most useful but unfortunately underdiscussed concepts in the artificial intelligence space relative to the modern generative AI gigahype. Embeddings are a set of hundreds of numbers which uniquely correspond to a given object that define its dimensionality, nowadays in a multiple of 128 such as 384D, 768D, or even 1536D. The larger the embeddings, the more “information” and distinctiveness each can contain, in theory.

These embeddings can be used as-is for traditional regression and classification problems with your favorite statistical modeling library, but what’s really useful about these embeddings is that if you can find the minimum mathematical distance between a given query embedding and another set of embeddings, you can then find which is the most similar: extremely useful for many real-world use cases such as search.

You wanna cut through the hype about AI? Here's the key takeaway: it boils down to a bunch of math nerds figuring out interesting relationships between numbers.

Which, of course, is useless to all of us non-math nerds... except for when you apply this information in the context of Pokémon.

Joking aside, I have a basic understanding of embeddings, but this article, with its basis in Pokémon lore, is the clearest explanation for how embeddings work in practice that I’ve seen.

Warning: there's still a lot of involved math happening here, but stay with it. You might learn a concept or two!

The University of Minnesota’s Twin Cities campus is massive.

When I went there, I was told it was the third largest university in the country based off square footage.

The Minneapolis campus alone has an east bank and a west bank, connected by a bridge with a top that is for pedestrian use only.

I used to live in the Como neighborhood. It was a 30 minute walk from my house to the classes I had on the west bank. I could also take the 3, which made it more like a 5 minute bus ride.

My preferred method of transportation, which I would use up until the snow made it infeasible, was my bike.

When I moved down to campus for the first time, my dad wouldn’t let me bring my Specialized bike that he got for me in seventh grade.

Instead, he insisted on buying me a $99 Schwinn bike from Target. It weighed a ton and the brakes weren’t great, but it certainly got me from A to B.

I recently got rid of that bike, and it felt like getting rid of a car. In both cases, I usually get overcome with emotions such as grief from nostalgia, guilt from abandoning something I knew so intimately, and gratitude for being able to get so much life out of it.

One of the first times I put that bike to use was to attend a class on the west bank.

When I arrived at the beginning of the Washington Avenue Bridge, I was greeted by a spectacular view of the Minneapolis skyline.

The combination of that skyline, the breeze, and the views of the river below forced this song in my head.

I started singing it out loud, unable to place where I knew it from.

After having the same moment play out over the course of a semester, it finally dawned on me that I knew that song from hours of riding my bike in Pokémon.

Pure joy. That’s what this song reminds me of.

Even this evening, when I rode bikes with my family up to try the new ice cream shop in town, I got this song stuck in my head.

It truly is the perfect song for a bike trip.