The terminology voting actually comes from, so we borrow the term from error correction as an information theory. So let's say you want to communicate a classical bit, zero or one over some channel. It can randomly flip the bit with some probability. To achieve better accuracy, there is something called the repetition code. The probability of making an error reduces exponentially as the repetition time grows larger. Each shape or each module is an imperfect algorithm of module addition. One module alone cannot make mistakes on some examples,. But by aggregating these three modules together, or when I say vote, I actually mean aggregating. Just the last linear layer aggregates the results.

Get the Snipd
podcast app

Unlock the knowledge in podcasts with the podcast player of the future.
App store bannerPlay store banner

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode

Save any
moment

Hear something you like? Tap your headphones to save it with AI-generated key takeaways

Share
& Export

Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode