Computer-Generated New Yorker Cartoons Are Delightfully Weird

Cartoons in The New Yorker are iconic enough that you easily recognize one outside of the magazine. Even as the jokes are crowdsourced, the same style endures. Could an algorithm learn the style well enough to produce New Yorker cartoons? Introducing: The Neural Yorker.

Paying on their ubiquity and familiarity, comics artist Ilan Manouach and AI engineer Ioannis Siglidis developed the Neural Yorker, an artificial intelligence (AI) engine that posts computer-generated cartoons on Twitter. The project consists of image-and-caption combinations produced by a generative adversarial network (GAN), a deep-learning-based model. The network is trained using a database of punchlines and images of cartoons found online and then “learns” to create new gags in the New Yorker‘s iconic style, with hilarious (and sometimes unsettling) results.

The comics are not conventionally as funny as the real New Yorker cartoons, but their very weirdness may provoke giggles. And when they come a little too close to human experiences, those giggles can become a sense of dread. Read about The Neural Yorker project at Hyperallergic, and follow its Twitter account to see what it comes up with next. -via Damn Interesting

Listen beautiful relax classics on our Youtube channel.

Source: neatorama

No votes yet.
Please wait...