News Daily

The Times

Australia

  • Written by The Conversation
Researchers trained an AI model to 'think' like a baby, and it suddenly excelled

In a world rife with opposing views, let’s draw attention to something we can all agree on: if I show you my pen, and then hide it behind my back, my pen still exists – even though you can’t see it anymore. We can all agree it still exists, and probably has the same shape and colour it did before it went behind my back. This is just common sense.

These common-sense laws of the physical world are universally understood by humans. Even two-month-old infants share this understanding. But scientists are still puzzled by some aspects of how we achieve this fundamental understanding. And we’ve yet to build a computer that can rival the common-sense abilities of a typically developing infant.

New research by Luis Piloto and colleagues at Princeton University – which I’m reviewing for an article in Nature Human Behaviour – takes a step towards filling this gap. The researchers created a deep-learning artificial intelligence (AI) system that acquired an understanding of some common-sense laws of the physical world.

The findings will help build better computer models that simulate the human mind, by approaching a task with the same assumptions as an infant.

Childish behaviour

Typically, AI models start with a blank slate and are trained on data with many different examples, from which the model constructs knowledge. But research on infants suggests this is not what babies do. Instead of building knowledge from scratch, infants start with some principled expectations about objects.

For instance, they expect if they attend to an object that is then hidden behind another object, the first object will continue to exist. This is a core assumption that starts them off in the right direction. Their knowledge then becomes more refined with time and experience.

The exciting finding by Piloto and colleagues is that a deep-learning AI system modelled on what babies do, outperforms a system that begins with a blank slate and tries to learn based on experience alone.

Read more: Artificial intelligence can deepen social inequality. Here are 5 ways to help prevent this

Cube slides and balls into walls

The researchers compared both approaches. In the blank-slate version, the AI model was given several visual animations of objects. In some examples, a cube would slide down a ramp. In others, a ball bounced into a wall.

The model detected patterns from the various animations, and was then tested on its ability to predict outcomes with new visual animations of objects. This performance was compared to a model that had “principled expectations” built in before it experienced any visual animations.

These principles were based on the expectations infants have about how objects behave and interact. For example, infants expect two objects should not pass through one another.

If you show an infant a magic trick where you violate this expectation, they can detect the magic. They reveal this knowledge by looking significantly longer at events with unexpected, or “magic” outcomes, compared to events where the outcomes are expected.

Infants also expect an object should not be able to just blink in and out of existence. They can detect when this expectation is violated as well.

A baby makes a comical 'shocked' face, with wide eyes and an open mouth.
Infants can detect when objects seem to defy the basic laws governing the physical world. Shutterstock

Piloto and colleagues found the deep-learning model that started with a blank slate did a good job, but the model based on object-centred coding inspired by infant cognition did significantly better.

The latter model could more accurately predict how an object would move, was more successful at applying the expectations to new animations, and learned from a smaller set of examples (for example, it managed this after the equivalent of 28 hours of video).

An innate understanding?

It’s clear learning through time and experience is important, but it isn’t the whole story. This research by Piloto and colleagues is contributing insight to the age-old question of what may be innate in humans, and what may be learned.

Beyond that, it’s defining new boundaries for what role perceptual data can play when it comes to artificial systems acquiring knowledge. And it also shows how studies on babies can contribute to building better AI systems that simulate the human mind.

Read more https://theconversation.com/researchers-trained-an-ai-model-to-think-like-a-baby-and-it-suddenly-excelled-186563

Split Corrugated Conduit for Flexible Cable Protection

For wiring assemblies in vehicles, machinery and equipment, choosing suitable cable protection helps keep cables organised and reduces direct contact with surrounding parts. Mojak Plastics supplies plastic tubing and conduit options for different installation needs, and split corrugated conduit can... Read more

Trailers Melbourne Buyers Can Compare: When Box Trailers Make Sense

For many homeowners, businesses and tradespeople, trailers Melbourne customers use every week need to be versatile enough for changing loads. A box trailer can be particularly useful because its enclosed sides help contain cargo while providing a straightforward loading area... Read more

Bottle Label Printing That Balances Design and Readability

Product labels need to attract attention while making information easy to find and understand. On a bottle, the available space may be limited by the container’s shape, so every design decision matters. Bottle label printing should account for visual hierarchy... Read more

Office Cleaning Melbourne: Planning a Consistent Workplace Routine

Businesses looking for office cleaning Melbourne need a plan that reflects the way their workplace operates. A clean office supports day-to-day organisation, helps shared spaces remain presentable and gives employees and visitors a more orderly environment. Eco Green Cleaning Management... Read more

Pinboard Solutions for Offices, Schools and Shared Information Spaces

Why a Pinboard Remains Useful A pinboard provides a simple way to display information that needs to remain visible without being rewritten. Lawdex supplies fabric and cork options for offices, schools, staff areas and other environments. A pinboard can be used... Read more

Retractable Hose Reel: A Practical Guide To Choosing The Right Hose Storage

A retractable hose reel can make hose storage more organised, accessible and practical in workshops, commercial facilities, service areas and other working environments. Instead of leaving a hose coiled across the floor or requiring staff to manually wind it after... Read more