Human infants are fascinated by other people. They bring to this fascination a constellation of rich and flexible expectations about the intentions motivating people’s actions. In a new study, scientists from New York University and Stanford University tested 11-month-old infants and state-of-the-art learning-driven neural-network models on the Baby Intuitions Benchmark, a suite of tasks challenging both infants and machines to make high-level predictions about the underlying causes of agents’ actions. Their results, which highlight fundamental differences between cognition and computation, point to shortcomings in today’s technologies and where improvements are needed for artificial intelligence (AI) to more fully replicate human behavior.
“Adults and even infants can easily make reliable inferences about what drives other people’s actions,” said Dr. Moira Dillon, a researcher at New York University.
“Current AI finds these inferences challenging to make.”
“The novel idea of putting infants and AI head-to-head on the same tasks is allowing researchers to better describe infants’ intuitive knowledge about other people and suggest ways of integrating that knowledge into AI.”
“If AI aims to build flexible, commonsense thinkers like human adults become, then machines should draw upon the same core abilities infants possess in detecting goals and preferences,” said Dr. Brenden Lake, also from New York University.
It’s been well-established that infants are fascinated by other people — as evidenced by how long they look at others to observe their actions and to engage with them socially.
In addition, previous studies focused on infants’ commonsense psychology — their understanding of the intentions, goals, preferences, and rationality underlying others’ actions — have indicated that infants are able to attribute goals to others and expect others to pursue goals rationally and efficiently.
The ability to make these predictions…
Read the full article here