https://www.nature.com/articles/d41586-022-01921-7 Skip to main content Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript. Advertisement Advertisement Nature * View all journals * Search * My Account Login * Explore content * About the journal * Publish with us Subscribe * Sign up for alerts * RSS feed 1. nature 2. news 3. article * NEWS * 11 July 2022 DeepMind AI learns simple physics like a baby Neural network could be a step towards programs for studying how human infants learn. * Davide Castelvecchi 1. Davide Castelvecchi View author publications You can also search for this author in PubMed Google Scholar * Twitter * Facebook * Email You have full access to this article via your institution. Download PDF Baby with building blocks. Even young babies are aware of the basic physics of everyday objects. Credit: Getty Inspired by research into how infants learn, computer scientists have created a program that can learn simple physical rules about the behaviour of objects -- and express surprise when they seem to violate those rules. The results were published on 11 July in Nature Human Behaviour^1. Developmental psychologists test how babies follow the motion of objects by tracking their gaze. When shown a video of, for example, a ball that suddenly disappears, the children express surprise, which researchers measure by how long they stare in a particular direction. Luis Piloto, a computer scientist at Google-owned company DeepMind in London, and his collaborators wanted to develop a similar test for artificial intelligence (AI). The team trained a neural network -- a type of software system that learns by spotting patterns in large amounts of data -- with animated videos of simple objects such as cubes and balls. The software model, named Physics Learning through Auto-encoding and Tracking Objects (PLATO), was fed the raw images from the videos, but also versions that highlighted each object in the scene. PLATO was designed to develop an internal representation of physical properties of the objects, such as their positions and velocities. The system was trained on around 30 hours of videos showing simple mechanisms such as a ball rolling down a slope or two balls bouncing off each other, and developed the ability to predict how those objects would behave in different situations. In particular, it learnt patterns such as continuity, in which an object follows an uninterrupted trajectory rather than magically teleporting from one place to another; solidity, which prevents two objects from penetrating each other; and persistence of the objects' shape. "At every step of a movie, it makes a prediction" about what will happen next, Piloto says. "As it gets further into the movie, the prediction becomes more accurate." Surprise! When shown videos with 'impossible' events, such as an object suddenly disappearing, PLATO could measure the difference between the video and its own prediction, providing a measure of surprise. Piloto says that PLATO is not designed as a model of infant behaviour, but that it could be a first step towards AI that can test hypotheses about how human babies learn. "We're hoping this can eventually be used by cognitive scientists to seriously model the behaviour of infants." Comparing AI with how human infants learn is "an important research direction", says Jeff Clune, a computer scientist at the University of British Columbia in Vancouver. "That said, the paper does hand-design much of the prior knowledge that gives these AI models their advantage." Clune and other researchers are working on approaches in which the program develops its own algorithms for understanding the physical world. doi: https://doi.org/10.1038/d41586-022-01921-7 Read the related News & Views, 'Can a computer think like a baby?' References 1. Piloto, L. S., Weinstein, A., Battaglia, P. & Botvinick, M. Nature Hum. Behav. https://doi.org/10.1038/s41562-022-01394-8 (2022). Article Google Scholar Download references Related Articles * DeepMind's AI helps untangle the mathematics of knots * [d41586-022] What's next for AlphaFold and the AI protein-folding revolution * [d41586-022] Machine learning helps to identify the animals that deadly viruses call home * AI Copernicus 'discovers' that Earth orbits the Sun * Medical students need artificial intelligence and machine learning training Subjects * Computer science * Physics * Psychology Latest on: Computer science These 'quantum-proof' algorithms could safeguard against future cyberattacks These 'quantum-proof' algorithms could safeguard against future cyberattacks News 08 JUL 22 Building neural networks that smell like a brain Building neural networks that smell like a brain Outlook 22 JUN 22 Open-source language AI challenges big tech's models Open-source language AI challenges big tech's models News 22 JUN 22 Physics These 'quantum-proof' algorithms could safeguard against future cyberattacks These 'quantum-proof' algorithms could safeguard against future cyberattacks News 08 JUL 22 Direct observation of vortices in an electron fluid Direct observation of vortices in an electron fluid Article 06 JUL 22 Coherent interfaces govern direct transformation from graphite to diamond Coherent interfaces govern direct transformation from graphite to diamond Article 06 JUL 22 Psychology Guatemala's COVID vaccine roll-out failed: here's what researchers know Guatemala's COVID vaccine roll-out failed: here's what researchers know News 07 JUL 22 A synergistic mindsets intervention protects adolescents from stress A synergistic mindsets intervention protects adolescents from stress Article 06 JUL 22 Sniffing out smell's effects on human behaviour Sniffing out smell's effects on human behaviour Outlook 22 JUN 22 Nature Careers Jobs * Faculty Position in Microbial Pathogenesis Northwestern University (NU) Chicago, IL, United States * Assistant Professor, Computational Oncology (Non Tenure Line-Research in Radiation Oncology) Stanford Medicine Palo Alto, CA, United States * Director of Bone & Soft Tissue Pathology University of Michigan (U-M) Ann Arbor, MI, United States * Call for nominations | Canada Excellence Research Chairs (CERC) Universite du Quebec a Trois-Rivieres Trois-Rivieres, Quebec, Canada You have full access to this article via your institution. Download PDF Related Articles * DeepMind's AI helps untangle the mathematics of knots * [d41586-022] What's next for AlphaFold and the AI protein-folding revolution * [d41586-022] Machine learning helps to identify the animals that deadly viruses call home * AI Copernicus 'discovers' that Earth orbits the Sun * Medical students need artificial intelligence and machine learning training Subjects * Computer science * Physics * Psychology Advertisement Sign up to Nature Briefing An essential round-up of science news, opinion and analysis, delivered to your inbox every weekday. Email address [ ] [ ] Yes! Sign me up to receive the daily Nature Briefing email. I agree my information will be processed in accordance with the Nature and Springer Nature Limited Privacy Policy. Sign up * Close Nature Briefing Sign up for the Nature Briefing newsletter -- what matters in science, free to your inbox daily. Email address [ ] Sign up [ ] I agree my information will be processed in accordance with the Nature and Springer Nature Limited Privacy Policy. Close Get the most important science stories of the day, free in your inbox. Sign up for Nature Briefing Explore content * Research articles * News * Opinion * Research Analysis * Careers * Books & Culture * Podcasts * Videos * Current issue * Browse issues * Collections * Subjects * Follow us on Facebook * Follow us on Twitter * Subscribe * Sign up for alerts * RSS feed About the journal * Journal Staff * About the Editors * Journal Information * Our publishing models * Editorial Values Statement * Journal Metrics * Awards * Contact * Editorial policies * History of Nature * Send a news tip Publish with us * For Authors * For Referees * Submit manuscript Search Search articles by subject, keyword or author [ ] Show results from [All journals] Search Advanced search Quick links * Explore articles by subject * Find a job * Guide to authors * Editorial policies Nature (Nature) ISSN 1476-4687 (online) ISSN 0028-0836 (print) nature.com sitemap Nature portfolio * About us * Press releases * Press office * Contact us * * * Discover content * Journals A-Z * Articles by subject * Nano * Protocol Exchange * Nature Index Publishing policies * Nature portfolio policies * Open access Author & Researcher services * Reprints & permissions * Research data * Language editing * Scientific editing * Nature Masterclasses * Nature Research Academies * Research Solutions Libraries & institutions * Librarian service & tools * Librarian portal * Open research * Recommend to library Advertising & partnerships * Advertising * Partnerships & Services * Media kits * Branded content Career development * Nature Careers * Nature Conferences * Nature events Regional websites * Nature Africa * Nature China * Nature India * Nature Italy * Nature Japan * Nature Korea * Nature Middle East Legal & Privacy * Privacy Policy * Use of cookies * Manage cookies/Do not sell my data * Legal notice * Accessibility statement * Terms & Conditions * California Privacy Statement Springer Nature (c) 2022 Springer Nature Limited