How Can Babies’ Learning Help Teach AI?

Babies can help unlock the next generation of artificial intelligence (AI), according to Trinity College neuroscientists and colleagues.

The research, published today [Wednesday 22 June 2022 ] in the journal Nature Machine Intelligenceexamines the neuroscience and psychology of infant learning and distills three principles to guide the next generation of AI, which will help overcome the most pressing limitations of machine learning.

Dr Lorijn Zaadnoordijk, Marie Skłodowska-Curie Research Fellow at Trinity College explained: “Artificial Intelligence (AI) 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 in AI 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 that learn the machines must be painstakingly curated by humans. But we know that learning can be done much more efficiently, because infants don’t learn this way! They are somehow experiencing the world.

In their article “Unsupervised machine learning for lessons”, Dr Lorijn Zaadnoordijk and Professor Rhodri Cusack, from the Trinity College Institute of Neuroscience, and Dr Tarek R. Besold from TU Eindhoven, The Netherlands, argue that better ways to learn unstructured data are needed. For the first time, they make inflatable learning from specific insights about what concrete proposals to make and how to apply these learnings to apply them effectively.

Machines, they say, 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. And, like infants, they need to have a developmental trajectory, where they “grow up” as experiences and networks change.

Dr. Tarek R. Besold, Researcher, Philosophy & Ethics Group at TU Eindhoven, said: “As AI researchers we often draw metaphorical parallels between our systems and the mental development of human babies and children. It is high time to take these analogies with more detail and look at the rich knowledge of infant development from psychology and neuroscience, which may help us overcome the most pressing limitations of machine learning. ”

Professor Rhodri Cusack, The Thomas Mitchell Professor of Cognitive Neuroscience, Director of the Trinity College Institute of Neuroscience added: Artificial neural networks were the brain that inspired parts. Similar to infants, they rely on learning, but current implementations are very different from human (and animal) learning. Through interdisciplinary research, babies can help unlock the next generation of AI. ”

Reference: Zaadnoordijk L, Besold TR, Cusack R. Unsupervised machine learning for infant learning from lessons. Nat Mach Intell. 2022; 4 (6): 510-520. doi: 10.1038 / s42256-022-00488-2

This article has been republished from the following materials. Note: Material may have been edited for length and content. For further information, please contact the cited source.

Leave a Reply

Your email address will not be published.

Back to top button