search
HomeTechnology peripheralsAIMake AI think like a baby! DeepMind 'Plato” model published in Nature sub-journal

Make AI think like a baby! DeepMind 'Plato” model published in Nature sub-journal

Paper address: https://www.nature.com/articles/s41562-022-01394-8

However, before talking about this project, we need to Let me give an example first to make it easier for everyone to understand.

If I stand in front of you with a pen, and then I hide the pen behind my back, will you not be able to see the pen?

But the pen must still exist, right?

Make AI think like a baby! DeepMind 'Plato” model published in Nature sub-journal

Such a simple truth, not only you understand it, but even a two-month-old baby understands it.

But the reason behind it is very intriguing. Scientists are curious, why do people naturally understand this principle?

The story of DeepMind starts from this simple curiosity.

Do you think babies don’t understand anything?

We call "the pen cannot be seen after being put down but the pen is still there" as one of the thousands of common sense in physics, and DeepMind scientists want to compare common sense in physics between AI and babies.

Luis Piloto of Princeton University and his colleagues developed a deep learning AI system that can understand some common-sense laws of the physical world.

In this way, future computer models can better imitate human thinking and solve problems with a model that has the same cognition as a baby.

In general, any AI model starts with a blank piece of paper, and then uses a variety of examples to train the model. From the input data and examples, the model generates knowledge.

However, scientists point out that this is not the case for babies.

Babies do not learn things from scratch, but they are born with some prejudgments about objective things.

Let’s take the hidden pen above as an example. Babies innately know that even if the pen is hidden, it will still be there.

This is the underlying logic of the next experiment. That is: babies have some core assumptions when they are born, and these assumptions will allow them to develop in the right direction as they grow up, and their knowledge will become better and better as time goes by and experience increases. Come more refined.

This gave the Piloto team inspiration.

Piloto wondered, would a deep learning artificial intelligence model that imitates infant behavior patterns perform better than an artificial intelligence model that starts with a blank sheet of paper and relies solely on experience learning?

The researchers further compared the two different models.

The first thing they did was the traditional method (referred to as a blank sheet of paper). They gave the AI ​​model some visual animations of objects and let the AI ​​learn, such as a block sliding down a slope, or a ball bouncing against a wall.

The AI ​​model detected movement patterns in these animations, and the researchers then set out to test whether the model could predict the movement of other objects.

On the other hand, the artificial intelligence model that imitates babies has some "principles" at the beginning, and the source of these "principles" is some innate assumptions of babies about the movement and interaction between objects.

To give a simple example, babies know that two objects cannot pass through each other, an object cannot rise out of thin air, etc.

AI that imitates infant cognition——"Plato"

In fact, the common sense of physics that infants know innately goes beyond the two points mentioned above. The full version is the following five points:

1. Continuity: Objects do not travel from one place to another, but have a certain continuous path in time and space.

2. Object persistence: Objects will not disappear when out of sight.

3. Solidity: Objects do not penetrate each other.

4. Immutability: The properties of the object (such as shape) will not change.

5. Directional inertia: The path of object motion is consistent with the principle of inertia.

Make AI think like a baby! DeepMind 'Plato” model published in Nature sub-journal

Based on these five points of knowledge, if you perform a magic trick or something for babies, and then something goes against their preset knowledge, they will know that you are doing it. They are clever and know that counter-intuitive phenomena are not the way things are.

Although, babies are still not as knowledgeable as older children. Babies will observe counter-common sense phenomena for a long time, and then compare them with their own preset cognitions, and finally conclude that someone is doing tricks. in conclusion.

Speaking of this, I can’t help but think of a very popular video. My parents hid behind the sheets, shook the sheets up and down a few times, and quickly hid in the room behind them while hiding behind the sheets. When the baby doesn't see his parents after the sheets disappear, he will stand there and think for a while, wondering where his parents have gone.

There is another interesting point here. That is, babies will express "surprise" after seeing counterintuitive phenomena. This sounds obvious, but the researchers also replicated this unique performance in AI.

With these foundations in mind, let’s look at the experimental results.

The AI ​​model designed by Piloto is called PLATO (Physics Learning through Auto-encoding and Tracking Objects), which is "Plato".

PLATO was trained on almost 30 hours of videos showing how objects perform some simple movements, and then trained the model to predict the movements of these objects in different situations.

Make AI think like a baby! DeepMind 'Plato” model published in Nature sub-journal

What’s interesting is that the model finally learned the five common sense points of physics mentioned above.

When there is something counter-intuitive in the video you are watching, PLATO can also show a certain degree of surprise like a baby.

Piloto and his colleagues found that the AI ​​model using the traditional training method (a blank piece of paper) performed well, but it was not as good as the unknown and was shocked by the comparison. PLATO, an AI model that imitates babies, performed much better.

Because of the blessing of preset cognition, the latter model can more accurately predict the movement of an object, apply the preset cognition to new object movement animations, and train the model The size of the data set used will also be smaller.

The Piloto team concluded that although learning and experience accumulation are important, it is not everything.

Their research points directly to a classic question - what is innate in humans and what is learned.

The next step is to apply this kind of human cognition to AI research.

Piloto has shown us the excellent results of the new method.

However, Piloto emphasized that PLATO is not designed to be a baby behavior model. We are just borrowing some methods of baby cognition to feed artificial intelligence.

Make AI think like a baby! DeepMind 'Plato” model published in Nature sub-journal

PLATO’s simulation system: feedforward perception module (left) and loop dynamic predictor module (right)

Jeff, a computer scientist at the University of British Columbia in Vancouver Clune also said that combining AI with the learning methods of human infants is an important direction.

At this moment, Clune is working with other researchers to develop their own algorithmic methods for understanding the physical world.

Author introduction

Luis Piloto is the first author of the paper and the corresponding author.

Make AI think like a baby! DeepMind 'Plato” model published in Nature sub-journal

He received a bachelor's degree in computer science from Rutgers University in 2012, and then went to Princeton University to study, and received master's degrees in neuroscience in 2017 and 2021 respectively. Ph.D.

In 2016, he officially joined DeepMind and became a research scientist.

Make AI think like a baby! DeepMind 'Plato” model published in Nature sub-journal

The above is the detailed content of Make AI think like a baby! DeepMind 'Plato” model published in Nature sub-journal. For more information, please follow other related articles on the PHP Chinese website!

Statement
This article is reproduced at:51CTO.COM. If there is any infringement, please contact admin@php.cn delete
How to Build Your Personal AI Assistant with Huggingface SmolLMHow to Build Your Personal AI Assistant with Huggingface SmolLMApr 18, 2025 am 11:52 AM

Harness the Power of On-Device AI: Building a Personal Chatbot CLI In the recent past, the concept of a personal AI assistant seemed like science fiction. Imagine Alex, a tech enthusiast, dreaming of a smart, local AI companion—one that doesn't rely

AI For Mental Health Gets Attentively Analyzed Via Exciting New Initiative At Stanford UniversityAI For Mental Health Gets Attentively Analyzed Via Exciting New Initiative At Stanford UniversityApr 18, 2025 am 11:49 AM

Their inaugural launch of AI4MH took place on April 15, 2025, and luminary Dr. Tom Insel, M.D., famed psychiatrist and neuroscientist, served as the kick-off speaker. Dr. Insel is renowned for his outstanding work in mental health research and techno

The 2025 WNBA Draft Class Enters A League Growing And Fighting Online HarassmentThe 2025 WNBA Draft Class Enters A League Growing And Fighting Online HarassmentApr 18, 2025 am 11:44 AM

"We want to ensure that the WNBA remains a space where everyone, players, fans and corporate partners, feel safe, valued and empowered," Engelbert stated, addressing what has become one of women's sports' most damaging challenges. The anno

Comprehensive Guide to Python Built-in Data Structures - Analytics VidhyaComprehensive Guide to Python Built-in Data Structures - Analytics VidhyaApr 18, 2025 am 11:43 AM

Introduction Python excels as a programming language, particularly in data science and generative AI. Efficient data manipulation (storage, management, and access) is crucial when dealing with large datasets. We've previously covered numbers and st

First Impressions From OpenAI's New Models Compared To AlternativesFirst Impressions From OpenAI's New Models Compared To AlternativesApr 18, 2025 am 11:41 AM

Before diving in, an important caveat: AI performance is non-deterministic and highly use-case specific. In simpler terms, Your Mileage May Vary. Don't take this (or any other) article as the final word—instead, test these models on your own scenario

AI Portfolio | How to Build a Portfolio for an AI Career?AI Portfolio | How to Build a Portfolio for an AI Career?Apr 18, 2025 am 11:40 AM

Building a Standout AI/ML Portfolio: A Guide for Beginners and Professionals Creating a compelling portfolio is crucial for securing roles in artificial intelligence (AI) and machine learning (ML). This guide provides advice for building a portfolio

What Agentic AI Could Mean For Security OperationsWhat Agentic AI Could Mean For Security OperationsApr 18, 2025 am 11:36 AM

The result? Burnout, inefficiency, and a widening gap between detection and action. None of this should come as a shock to anyone who works in cybersecurity. The promise of agentic AI has emerged as a potential turning point, though. This new class

Google Versus OpenAI: The AI Fight For StudentsGoogle Versus OpenAI: The AI Fight For StudentsApr 18, 2025 am 11:31 AM

Immediate Impact versus Long-Term Partnership? Two weeks ago OpenAI stepped forward with a powerful short-term offer, granting U.S. and Canadian college students free access to ChatGPT Plus through the end of May 2025. This tool includes GPT‑4o, an a

See all articles

Hot AI Tools

Undresser.AI Undress

Undresser.AI Undress

AI-powered app for creating realistic nude photos

AI Clothes Remover

AI Clothes Remover

Online AI tool for removing clothes from photos.

Undress AI Tool

Undress AI Tool

Undress images for free

Clothoff.io

Clothoff.io

AI clothes remover

AI Hentai Generator

AI Hentai Generator

Generate AI Hentai for free.

Hot Article

R.E.P.O. Energy Crystals Explained and What They Do (Yellow Crystal)
1 months agoBy尊渡假赌尊渡假赌尊渡假赌
R.E.P.O. Best Graphic Settings
1 months agoBy尊渡假赌尊渡假赌尊渡假赌
Will R.E.P.O. Have Crossplay?
1 months agoBy尊渡假赌尊渡假赌尊渡假赌

Hot Tools

Safe Exam Browser

Safe Exam Browser

Safe Exam Browser is a secure browser environment for taking online exams securely. This software turns any computer into a secure workstation. It controls access to any utility and prevents students from using unauthorized resources.

WebStorm Mac version

WebStorm Mac version

Useful JavaScript development tools

SAP NetWeaver Server Adapter for Eclipse

SAP NetWeaver Server Adapter for Eclipse

Integrate Eclipse with SAP NetWeaver application server.

MinGW - Minimalist GNU for Windows

MinGW - Minimalist GNU for Windows

This project is in the process of being migrated to osdn.net/projects/mingw, you can continue to follow us there. MinGW: A native Windows port of the GNU Compiler Collection (GCC), freely distributable import libraries and header files for building native Windows applications; includes extensions to the MSVC runtime to support C99 functionality. All MinGW software can run on 64-bit Windows platforms.

Atom editor mac version download

Atom editor mac version download

The most popular open source editor