[/?utm_medium=email&utm_source=]

AI LEARNING THROUGH A BABY’S EYES  
[[link removed]]


 

Elizabeth Gibney
February 1, 2024
Nature [[link removed]]

*
[[link removed]]
*
[[link removed]]
*
*
[[link removed]]

_ A neural network that taught itself to recognize objects using the
filmed experiences of a single infant could offer new insights into
how humans learn. _

The artificial intelligence learned using video and audio from a
helmet-mounted camera worn by Sam — here aged 18 months, Credit: Wai
Keen Vong

 

An artificial intelligence (AI) model has learnt to recognize words
such as ‘crib’ and ‘ball’, by studying headcam recordings of a
tiny fraction of a single baby’s life.

The results suggest that AI can help us to understand how humans
learn, says Wai Keen Vong, co-author of the study and a researcher in
AI at New York University. This has previously been unclear, because
other language-learning models such as ChatGPT learn on billions of
data points, which is not comparable to the real-world experiences of
an infant, says Vong. “We don’t get given the internet when
we’re born.”

The authors hope that the research, reported in _Science_ on 1
February1
[[link removed]], will
feed into long-standing debates about how children learn language. The
AI learnt only by building associations between the images and words
it saw together; it was not programmed with any other prior knowledge
about language. That challenges some cognitive-science theories that,
to attach meaning to words, babies need some innate knowledge about
how language works, says Vong.

The study is “a fascinating approach” to understanding early
language acquisition in children, says Heather Bortfeld, a cognitive
scientist at the University of California, Merced.

Baby’s-eye view

Vong and his colleagues used 61 hours of recordings from a camera
mounted on a helmet worn by a baby boy named Sam, to gather
experiences from the infant’s perspective. Sam, who lives near
Adelaide in Australia, wore the camera for around one hour twice each
week (roughly 1% of his waking hours), from the age of six months to
around two years.

The researchers trained their neural network — an AI inspired by the
structure of the brain — on frames from the video and words spoken
to Sam, transcribed from the recording. The model was exposed to
250,000 words and corresponding images, captured during activities
such as playing, reading and eating. The model used a technique called
contrastive learning to learn which images and text tend to go
together and which do not, to build up information that can used to
predict which images certain words, such as ‘ball’ and ‘bowl’,
refer to.

To test the AI, the researchers asked the model to match a word with
one of four candidate images, a test that is also used to evaluate
children’s language abilities. It successfully classified the object
62% of the time — much better than the 25% expected by chance, and
comparable to a similar AI model that was trained on 400 million
image–text pairs from outside this data set.

For some words, such as ‘apple’ and ‘dog’, the model was able
to correctly identify previously unseen examples — something humans
generally find relatively easy. On average, it did so successfully 35%
of the time. The AI was better at identifying objects out of context
when they occurred frequently in the training data. It was also best
at identifying objects that vary little in their appearance, says
Vong. Words which can refer to a variety of different items — such
as ‘toy’ — were harder to learn.

Lessons about learning

The study’s reliance on data from a single child might raise
questions about the generalizability of its findings, because
childrens’ experiences and environments vary greatly, says Bortfeld.
But the exercise revealed that a lot can be learnt in the infant's
earliest days through only forming associations between different
sensory sources, she adds. The findings also challenge scientists —
such as US linguist Noam Chomsky — who claim that language is too
complex and the input of information is too sparse, for language
acquisition to happen through general learning processes. “These are
among the strongest data I’ve seen showing that such ‘special’
mechanisms are not necessary,” says Bortfeld.

[[link removed]]

DeepMind AI learns simple physics like a baby
[[link removed]]

Real-world language learning is much richer and varied than the AI
experienced. The researchers say that, because the AI is limited to
training on still images and written text, it could not experience
interactions that are inherent to a real baby’s life. The AI
struggled to learn the word ‘hand’ for example, which is usually
learnt early on in an infant’s life, says Vong. “Babies have their
own hands, they have a lot of experience with them. That’s
definitely a missing component of our model.”

“The potential for further refinements to make the model more
aligned with the complexities of human learning is vast, offering
exciting avenues for advancements in cognitive sciences,” says
Anirudh Goyal, a machine learning scientist at the University of
Montreal, Canada.

_doi: [link removed]

_More articles by Elizabeth Gibney
[[link removed]]_

References

*
Vong, W. K., Wang, W., Orhan, A. E. & Lake, B. M. _Science_ 383,
504–511 (2024).

* Science
[[link removed]]
* artificial intelligence
[[link removed]]
* language
[[link removed]]
* child development
[[link removed]]

*
[[link removed]]
*
[[link removed]]
*
*
[[link removed]]

 

 

 

INTERPRET THE WORLD AND CHANGE IT

 

 

Submit via web
[/contact/submit_to_xxxxxx?utm_medium=email&utm_source=]
Submit via email
Frequently asked questions [/faq?utm_medium=email&utm_source=]
Manage subscription [/subscribe?utm_medium=email&utm_source=]
Visit xxxxxx.org [/?utm_medium=email&utm_source=]

Twitter [[link removed]]

Facebook [[link removed]]

 




[link removed]

To unsubscribe, click the following link:
[link removed]