I am really really excited to announce a thing I’ve been working on for more than a year now: there’s going to be an AI Weirdness book!!!!! You can preorder it at these links: Amazon - Barnes & Noble - Indiebound - Powell’s - Tattered Cover When
I’ve used neural networks to name all kinds of things - halloween costumes, craft beers, cats, and even guinea pigs. The weirder the starting set of names, the more a neural network’s creations might blend in (although cats named “Jexley Pickle” and “Big Wiggy Bool” might at least
H.M.S. Neural NetOne of my favorite things to do with machine learning algorithms is to get them to name things. Give a neural network (a type of machine learning algorithm) enough examples, and it will do an often decent (sometimes howlingly bad) imitation of their letter combinations and
The other day I trained a neural net to generate the names of cookies, based on about 1,000 existing recipes. The resulting names (Quitterbread Bars, Hand Buttersacks, Low Fuzzy Feats, and more) were both delightfully weird and strangely plausible. People even invented delicious recipes for them. But given that
It is quite fitting that the idea to train a neural net to generate comics names came from the creator of a webcomic about a hapless AI robot. Aaron Uglum collected 1,417 names of newspaper comics from Wikipedia, and I gave them to textgenrnn to see if it could
I did one of these for 2017 last year, so I thought it would be fun to recap some of my favorite aiweirdness.com experiments from 2018. Sure, financial forecasting, facial recognition, and delivering ads may be the most common uses for machine learning, but that doesn’t mean they’
I am always amazed by all the corners of life that have their own naming conventions. What makes a name sound like an heirloom apple, or a cookie, or a Pokemon? Here’s one I had never thought much about: the names of fireworks. Bruce Preston spends the New Year
This seems to be a year for AI experiments centered around Christmas movies. MIT Technology Review generated some titles and plot summaries (I would probably watch The Christmas StorK) and Botnik Studios has been using predictive text to write weird new Christmas movie plots and summaries. So when Nicole Kobie
So I’ve used neural networks to generate recipes in the past. They’re computer programs that can learn to imitate the data we give them, copying the way that humans drive cars, label images, or translate languages. That is, they try to learn. They’re called “neural” because they
So there’s these computer programs called artificial neural networks that are good at imitating things. By seeing examples of what humans did, they can learn to translate languages, predict product sales, and even categorize text and images as innocuous or explicit (it has a lot of trouble with this