Hey my friends, this is the article 81 / 1000! For those who don’t know me, my name is Selim Chehimi and I’m an engineering student. I’ve been programming for 7 years now so you can tell that I really enjoy that. Those 7 years of programming lead me to Artificial Intelligence. My dream is to build an AI Startup so that’s the reason why I’m sharing this article with you. I hope that you’ll enjoy reading it as much as I’ve enjoyed writing it.
DeepMind is the greatest neuroscientist inspired AI company acquired by Google in 2014. It’s often described as a kind of Apollo program for AI because it gathers the best scientists and engineers to make quick progress in this domain. It’s the biggest collection of people working on AI’s issues today. One of DeepMind’s project was to build an AI that could create high-quality images from low-quality ones with an impressive approximation. The result was truly mind-blowing:
However, there were some limitations – the process was extremely slow and computationally expensive and the images were 32×32 or 64×64 at most.
DeepMind tried something new using the same technology (PixelCNN). Their latest breakthrough shows that their AI can create photorealistic pictures from human’s sentences. The results are as follows for “A yellow bird with a black head, orange eyes, and an orange bill”:
The cool part lies in the fact that these new images are significantly different than the images the AI has been given in the beginning. Also, the more detailed your sentence is, the more detailed the result will be.
Thanks so much for reading, that’s the end of Article 81. Please, share it and don’t forget to follow me on social media. You can also subscribe to my newsletter below to never miss any article. Don’t hesitate to tell me what you think of this Article in the comments and stay tuned for another one tomorrow!