An experiment described in the latest issue of the journal Science showed that an artificial intelligence model was able to learn a variety of words and concepts using just 1% of the time a child spends awake.
Unlike children who are exposed to millions of words each year, the best AI systems are trained on trillion-word texts. But researchers have shown that an AI model trained using small slices of a child’s daily life can significantly expand our understanding of early language and conceptual development.
The multimodal neural network was trained on video recordings from a lightweight head-mounted camera that captured a child’s visual and auditory experiences from six months to two years of age. The study’s findings show that AI can associate words with their visual images based on limited data about a child’s daily experiences.
Source: Ferra
I am a professional journalist and content creator with extensive experience writing for news websites. I currently work as an author at Gadget Onus, where I specialize in covering hot news topics. My written pieces have been published on some of the biggest media outlets around the world, including The Guardian and BBC News.
