Scientists have created an AI that can think like a human baby

Artificial intelligence (AI) systems are already far ahead of us in certain areas – playing Go, for example, or crunching large sets of data – but in other respects AI is still a long way from human beings, still only a few months away after we were born.

For example, even young infants instinctively know that an object that briefly passes another does not have to disappear and reappear elsewhere. Presented with such a magical act, babies act surprised.

But such a simple rule of continuity, along with other basic physical laws, has not been so intuitive to AI. Now a new study introduces an artificial intelligence called PLATO, which is inspired by research into how babies learn – and can think a lot like a human baby.

PLATO stands for “Physics Learning through Automatic Coding and Object Tracking” and was trained through a series of coded videos designed to represent the same basic knowledge that babies have in their first months of life.

“Fortunately for us, developmental psychologists have spent decades studying what babies know about the physical world and cataloging the different components or concepts that go into physical meaning,” says neuroscientist Luis Piloto, from the AI ​​research lab DeepMind in the UK.

“Extending their work, we built and open-sourced a physical concepts dataset. This synthetic video dataset takes inspiration from the original development experiments to evaluate physical concepts in our models.”

There are three key concepts that we all understand from a very young age: permanence (objects will not suddenly disappear); solidity (solid objects cannot cross each other); and continuity (objects move steadily through space and time).

The data the researchers constructed covered these three concepts, plus two additional ones: immutability (object properties, such as shape, do not change); and directional inertia (objects move in a way that is consistent with the principles of inertia).

These concepts were demonstrated through ball clips falling to the ground, bouncing off each other, disappearing behind other objects and then reappearing, and so on. Having trained PLATO on these videos, the next step was to test it.

When the AI ​​was shown videos of ‘impossible’ scenarios that contradicted the physics it had learned, PLATO expressed surprise (or its AI equivalent): it was smart enough to realize that something strange had happened that broke the laws of physics.

This occurred even after relatively short training periods, as little as 28 hours in some cases. Technically, just like in the infant studies, the researchers were looking for evidence of violation of expectation (VoE) signals, indicating that the AI ​​understood the concepts it was taught.

“Our object-based model exhibited robust VoE effects in all five concepts we studied, despite being trained on video data in which specific probe events did not occur,” the researchers write in their published paper.

The team ran further tests, this time using different objects than those in the training data. Again, PLATO showed a solid understanding of what should and shouldn’t happen, demonstrating that he could learn and expand on his basic training knowledge.

However, PLATO is not yet at the level of a three-month-old baby. There were fewer AI surprises when presented with scenarios that did not involve any objects, or when the test and training models were similar.

Additionally, the videos that PLATO was trained on included additional data to help it recognize objects and their motion in three dimensions.

It seems that some integrated knowledge is still needed to get the full picture – and that the ‘nature vs nurture’ question is something that developmental scientists are still asking in babies. The research could give us a better understanding of the human mind, as well as help us build a better representation of its AI.

“Our modeling work provides a proof-of-concept demonstration that at least some central concepts in intuitive physics can be acquired through visual learning,” the researchers write.

“Although research in some precoital [born in an advanced state] species suggest that some basic physical concepts may be present from birth, in humans the data suggest that intuitive knowledge of physics emerges early in life but may be influenced by visual experience.”

The research was published in Nature Human behavior.

Leave a Comment

Your email address will not be published.