1.

2.

3.

4.

Janelle Shane is a research scientist in optics and recently conducted a very funny Valentines’s Day experiment. As she explained in her Tumblr post, “I collected all the genuine heart messages I could find, and then gave them to a learning algorithm called a neural network. Given a set of data, a neural network will learn the patterns that let it imitate the original data – although its imitation is sometimes imperfect. The candy heart messages it produced… well, you be the judge.”

1. The neural net did produce some that would pass for – and arguably improve upon – the standard messages.
2. Others were in the same spirit, but perhaps not quite as effective.
3. Others were, um, strange. I don’t know what they mean, but some of them might work on me.
4. These will probably not be one of the standard messages anytime soon.

Turns out, AI still has a little ways to go before it can start writing our Valentine’s greetings. On that note, wishing you a very happy Valentine’s Day!