Can AI get common sense? Facebook model shows the way

(IANS) In an advance to building machines with common sense, Facebook researchers have developed a new Artificial Intelligence (AI) model that can learn from any random group of images on the Internet without the need for careful curation and labelling that goes into most computer vision training today.

Called SEER (Self-supERvised), the “self-supervised” computer vision model was fed on a billion random, unlabelled and uncurated public Instagram images, Facebook said on Thursday.

The future of AI is in creating systems that can learn directly from whatever information they are given — whether it is text, images, or another type of data — without relying on carefully curated and labelled data sets to teach them how to recognise objects in a photo, interpret a block of text, or perform any of the countless other tasks that we ask it to.

This approach is known as self-supervised learning.

According to Facebook AI’s Chief Scientist Yann LeCun, the self-supervised learning approach is one of the most promising ways to build machines that have the background knowledge, or “common sense,” to tackle tasks that are far beyond today’s AI.

Facebook said that SEER outperformed the most advanced, state-of-the-art self-supervised systems in tests.

SEER also outperformed state-of-the-art supervised models on downstream tasks, including object detection, segmentation, and image classification.

The AI model’s performance demonstrates that self-supervised learning can excel at computer vision tasks in real-world settings.

This is a major breakthrough that ultimately clears the path for more flexible, accurate, and adaptable computer vision models in the future, the social networking giant said.

The findings were detailed in a paper published at arxiv.org.

The social networking giant said that self-supervised learning has long been a focus for Facebook AI because it enables machines to learn directly from the vast amount of information available in the world, rather than just from training data created specifically for AI research.

“This will help us build AI that works well for more people around the world, adapts quickly to changing circumstances, extends to additional use cases, and much more,” Facebook said.

Was it worth reading? Let us know.