A physics student and an engineering student from Stanford fed 400,000 memes to a Long Short-Term Memory Recurrent Neural Network and asked it to generate more memes of its own.
It did a pretty good job.
We acknowledge that one of the greatest challenges in our project and other language modeling tasks is to capture humor, which varies across people and cultures. In fact, this constitutes a research area on its own, as seen in publishings such as , and accordingly new research ideas on this problem should be incorporated into the meme generation project in t he future. One example would be to train on a dataset that includes the break point in the text be tween upper and lower for the image. These were chosen manually here and are important for the hum or impact of the meme. If the model could learn the breakpoints this would be a huge improvement and could fully automate the meme generation. Another avenue for future work would be to explo re visual attention mechanisms that operate on the images and investigate their role in meme gene ration tasks, based on publishings such as ,  and . Lastly we note that there was a bias in the dataset towards expletive, racist and sexist memes, so yet another possibility for future work would be to address this bias.
Dank Learning: Generating Memes Using Deep Neural Networks [Abel L Peirson V and E Meltem Tolunay/Stanford/Arxiv]
(via Four Short Links)
In 1975, Noam Chomsky and Jean Paiget held a historic debate about the nature of human cognition; Chomsky held that babies are born with a bunch of in-built rules and instincts that help them build up the knowledge that they need to navigate the world; Piaget argued that babies are effectively blank slates that acquire […]
Tim Wu (previously) is a legal scholar best known for coining the term "Net Neutrality" -- his next book, The Curse of Bigness: Antitrust in the New Gilded Age (previously) challenges the accepted wisdom about today's digital monopolists, which is that they grew so big because of some underlying truth about online business ("first-mover advantage," […]
When you train a machine learning system, you give it a bunch of data -- a simulation, a dataset, etc -- and it uses statistical methods to find a way to solve some task: land a virtual airplane, recognize a face, match a block of text with a known author, etc.
In case you hadn’t noticed from the sleigh bell-heavy music and the hues on your Starbucks cup, the holiday season hasn’t shown any more patience this year. But that doesn’t need to be a bad thing, especially if you’re hoping to get a jump on your shopping. Retailers aren’t waiting til Black Friday to dish […]
What do you get for the techie who has everything? How about giving them a Raspberry Pi and letting them make pretty much anything. Or better yet, do it for yourself with the Ultimate Raspberry Pi eBook Bundle. This trove of ideas and education unlocks the unlimited potential of this mini-computer, whose affordability and versatility […]
Note-taking just caught up to the digital age. For most of us, writing freehand is quicker and more convenient than pecking away on a tablet, but what to do when you need those scribbles on file? Grab a Rocketbook Everlast Reusable Notebook, which seamlessly fuses analog and digital notes. Just jot down your thoughts, journals […]