Best examples of creative AI in photography, art, writing, music and games
What is creativity? If you look it up in the dictionary, it’s the use of imagination or original ideas to create something. Naturally, this has always been the prerogative of humans, beings who can dream big and visualize concepts. Lately, however, researchers have argued that creativity is not only the hallmark of humans, but also of artificial intelligence. AIs may not dream like we do but, in specific contexts, with key information at their fingertips, they can write, imagine, invent games or beat others. These are some of the most extraordinary creative AI examples.
For an AI, creativity is not exactly the power of imagination as much as the power of creation. Artificial intelligence uses past data to translate a certain event or environment, learning just enough to generate new things. Most of the time, convolutional neural networks receive immense amounts of data and are left to train using those as starting points. Algorithms need to see patterns in the input information to then generate new examples that might be plausible in a given context.
The answer is definitely Yes, if you accept the definition of creativity proposed by science. There are dozens of examples of this, some more successful than others, ranging from an AI that creates poems or stories to neural networks that can come up with names or bring old photos to life.
AI technology for photos
Take, for example, this “Deep Nostalgia” AI that turns old photos into video animations. Imagine a reverse iPhone Live Photos where instead of picking the best frame from a short video, the program takes a vintage portrait photo and puts it in motion.
Another way to bring old images to life is through colorization. So one team trained an AI to fill in the blanks in a way that actually sees the true colors of Abraham Lincoln, Albert Einstein, Frida Kahlo, or Bertrand Russell. The results are amazing!
Truly breathtaking is the next GAN effort! NVIDIA succeeded in producing new individuals, new human faces from photos of real people. Watch them and tell me if you can tell who is computer generated and who is a real person!
And the AI didn’t stop there. An AI powered by images of more than 1,000 classical sculptures succeeded in producing Dio, a unique sculpture. Ironically, Dio was built from the remains of the computer used to generate him.
Best AI Writers
I am not joking. After trying their hand at retouching, colorizing, and even creating portraits from “scratch,” the AI programs were put to writing. What? Pickup lines, poems, love songs and even horrors.
In this case, getting it right wasn’t the main goal. In fact, the teams training the neural networks were probably hoping for a good laugh at most.
What did they get?
Original ways to flirt, for starters. Then, two-line poems written after an in-depth study of more than 20 million words from 19th century poetry. Last, but not least, a love song no one should have to listen to – Despondency, tender love. It’s cringey, at best.
In stark contrast is this love poem of a machine driven by Microsoft researchers and Kyoto University professors. After being trained on thousands of images juxtaposed with human-written descriptions and poems on each image, the AI has written a decent piece that could pass for avant-garde.
However, Shelley is by far the most popular AI author. This time it was MIT that gave an AI the power to tell stories… and stories it wrote, from random snippets based on what it learned, to contributions on a given text. It all culminated when Shelley broke the fourth wall and invited Twitter users to help her write better and more.
Writing horror stories can seem like a fun, sometimes easy task. But defend your intentions to humans? It’s not for the faint of heart. Fortunately, GPT-3, OpenAI’s powerful new language generator, lacks heart and was able to speak to humanity in a deeply moving essay.
AI music generators
Going from poetry to music is child’s play. So researchers took it to the next level and gave AI the task of composing lyrics and even entire music albums.
One of them generated spooky music in time for Halloween. This AI-generated playlist’s uncanny resemblance to horror movie soundtracks has an explanation. MIT trained the neural network on thousands of songs from cult horror movies to produce a new sound. Scary or just unnatural? Listen here and let me know!
Another AI was trained to create a new Swift song. To handle this, the neural network was trained on a massive amount of Tay’s lyrics. Unfortunately, his creation could not pass for a TSwift song.
Taylor Swift wasn’t the only singer AI tried to replace onstage. Eminem and Kanye came next, although in their case it was more of a deepfake situation. Both artists changed paths and started rapping about female power. Discover their collaboration here!
Finally, this AI went beyond its musical skills. He helped an artist compose and produce an entire music album. No crew needed!
AI in games – what can it do?
Have you heard of the God of Go? You must have. AlphaGo is the strongest Go player in history and surprise, surprise, it’s not human. DeepMind, Alphabet’s AI development subsidiary, is the creator of Go’s most powerful AI player. to challenge a Go player. Indeed, he can play against his predecessor – already world champion – and beat him! Want to know more about this amazing program? Read about it here!
Beating humans at their own game is satisfying on its own, but coming up with a whole new game… well, that’s impressive. A neural network trained on data from over 400 existing sports created Speedgate and its logo!
For those who prefer more static hobbies, a knitting AI might come in handy. InverseKnit has shown it can do a more than decent job with fingerless gloves from a very specific type of acrylic yarn, but it would be easy to train it on more materials. Ultimately, the researchers would like to make InverseKnit available to the public.
AI Professions: Weird or Awesome?
Now if you think knitter is the weirdest job an AI can have, try again. A machine learning program simulated the voice and facial features of a well-known Chinese TV presenter, making the case for a non-stop TV host.
In another corner of the world, an advertising contest in Belgium had an AI judge on its panel to choose the winning campaign. Amazingly, the AI made the same choice as the human judges, proving its worth.
Finally, an AI took care of naming the adoptable kittens. Sure, some of his suggestions were downright terrifying like Warning Signs, Bones of The Master, and Kill All Humans, but the AI managed to come up with some ingenious ones.
This shows that artificial intelligence does not need to be inventive to be creative. For AI, the sky is the limit as long as humans fill this gap.