AI Algorithm Can Generate Images

Sunday, July 19, 2020 - 09:57

Researchers from OpenAI have developed an AI algorithm which is capable of automatically generating realistic-looking images from bits of pixels.

The achievement is the latest evidence that AI is increasingly able to learn from and copy the real world in ways that may eventually allow algorithms to create fictional images that are indistinguishable from reality, axios reports.

Based on a paper presented at International Conference on Machine Learning, researchers showed they could train the organization's GPT-2 algorithm on images.

GPT-2 is best known as a text-generating algorithm, capable of absorbing the structure of language by training on billions of words off the internet and then "writing" passable text from a simple prompt.

After training on images, the OpenAI algorithm — now called iGPT — could be fed a visual prompt in the form of half an image and then fill in the rest of it.

Unlike algorithms that use supervised learning, which requires laborious amounts of labeled data, iGPT and GPT-2 use unsupervised learning on unlabeled data. That means much less human effort.

As Karen Hao points out in MIT Tech Review, the fact that both iGPT and GPT-2 use the same algorithm for different purposes is early evidence of more generalizable machine intelligence — which is, after all, OpenAI's aim.


Popular News

Latest News