Stanford students break the stereotype of using artificial intelligence for research by training bot to make memes. They fed a computer with over 400,000 memes to teach it how to generate its own.
This method used for generating memes using deep learning is known as Dank Learning. When they finished training the AI-Bot, they used it and called the generated meme dank or funny.
ALSO READ: Apple’s next iPhone to come with price tag of Rs 40,000?
The two researchers also wrote a white paper titled ‘Dank Learning: Generating Memes Using Deep learning’. The AI system used by the students is an image-captioning neutral network.
The duo, Abel L. Peirson (Physics Engineering department) and E. MeltemTolunay (Electrical Engineering department), fed the bot with memes that used, “advice animal” style memes where an image of a specific character is overlaid with a funny caption.
“In this paper, we specifically refer to meme generation as the task of generating a humorous caption in a manner that is relevant to the initially provided image, which can be a meme template or otherwise,” explained the researchers.
ALSO READ: Yahoo bids goodbye to Messenger App; says hi to Squirrel
The researchers had to test the ‘ Dankocity’ of the AI-generated memes that is they had to use humans to review the memes to determine if they were funny or not.
After the tests, Peirson and Tolunay concluded, “The average meme produced(by the AI bot) is difficult to differentiate from a real meme and both variants scored close to the same hilarity rating as real memes, although this is a fairly subjective metric,”