Trinity College scientists researched infant learning skills and how they can guide AI
Infants can help unlock the next generation of artificial intelligence (AI), research involving Trinity College Dublin neuroscientists suggests.
The research, published in the journal Nature Machine Intelligence, examines infant learning and distils three principles to guide the next generation of AI.
It is hoped these will help overcome the limitations of machine learning.
Dr Lorijn Zaadnoordijk, Marie Sklodowska-Curie Research Fellow at Trinity College, said: “Artificial intelligence has made tremendous progress in the last decade, giving us smart speakers, autopilots
in cars, ever-smarter apps and enhanced medical diagnosis.
“These exciting developments have been achieved thanks to machine learning, which uses enormous datasets to train artificial neural network models. However, progress is stalling in many areas because the datasets machines learn from must be painstakingly curated by humans.
“But we know learning can be done much more efficiently, because infants don’t learn this way. They learn by experiencing the world around them, sometimes by even seeing something just once.”
Machines will need in-built preferences to shape their learning from the beginning. They will need to learn from richer datasets that capture how the world is looking, sounding, smelling, tasting and feeling.
Like infants, they will need to have a developmental trajectory, where experiences and networks change as they “grow up”.
The article, “Lessons from infant learning for unsupervised machine learning”, was written by Dr Zaadnoordijk as well as Professor Rhodri Cusack, from the Trinity College Institute of Neuroscience, and Dr Tarek R Besold from TU Eindhoven, in the Netherlands.
Professor Rhodri Cusack said: “Artificial neural networks were in parts inspired by the brain.
“Similar to infants, they rely on learning, but current implementations are very different from human and animal learning.”