Liwaiwai Liwaiwai
  • /
  • Artificial Intelligence
  • Machine Learning
  • Robotics
  • Engineering
    • Architecture
    • Design
    • Software
    • Hybrid Cloud
    • Data
  • Learning
  • About
  • /
  • Artificial Intelligence
  • Machine Learning
  • Robotics
  • Engineering
    • Architecture
    • Design
    • Software
    • Hybrid Cloud
    • Data
  • Learning
  • About
Liwaiwai Liwaiwai
  • /
  • Artificial Intelligence
  • Machine Learning
  • Robotics
  • Engineering
    • Architecture
    • Design
    • Software
    • Hybrid Cloud
    • Data
  • Learning
  • About
  • Artificial Intelligence

AI Names Colors Much As Humans Do

  • March 26, 2021
  • liwaiwai.com

What the research is:

Across the thousands of different languages spoken by humans, the way we use words to represent different colors is remarkably consistent. For example, many languages have two distinct words for red and orange, but no language has many distinct commonly used words for various tonalities of orange. (Of course, if you visit a paint store, you’ll see dozens of esoteric names for different shades of orange. But these are rarely used in daily conversation.)

Using mathematical tools, linguistic researchers have shown this consistency in color names is because humans optimize language to balance the need for accurate communication with a general biological drive toward minimizing effort. Having extra color words — cantaloupe or burnt sienna, for example — adds complexity without significantly improving how effectively people communicate with each other.


Partner with liwaiwai.com
for your next big idea.
Let us know here.



From our partners:

CITI.IO :: Business. Institutions. Society. Global Political Economy.
CYBERPOGO.COM :: For the Arts, Sciences, and Technology.
DADAHACKS.COM :: Parenting For The Rest Of Us.
ZEDISTA.COM :: Entertainment. Sports. Culture. Escape.
TAKUMAKU.COM :: For The Hearth And Home.
ASTER.CLOUD :: From The Cloud And Beyond.
LIWAIWAI.COM :: Intelligence, Inside and Outside.
GLOBALCLOUDPLATFORMS.COM :: For The World's Computing Needs.
FIREGULAMAN.COM :: For The Fire In The Belly Of The Coder.
ASTERCASTER.COM :: Supra Astra. Beyond The Stars.
BARTDAY.COM :: Prosperity For Everyone.

Facebook AI has now shown that cutting-edge AI systems behave similarly. When two artificial neural networks are tasked with creating a way to communicate with each other about what colors they see, they develop systems that balance complexity and accuracy much as people do.

The images on the left show two color-naming systems created entirely by neural networks. Each cluster represents a color denoted by a single word. (The color shown is the average of the RGB values of all color chips in the cluster.) The top-left panel illustrates a three-word AI naming system, while the top-right panel shows a three-word human naming system — namely that of Wobé, a language spoken in Niger-Congo. The bottom-left panel illustrates a five-word AI naming system and the bottom-right panel shows the five-word naming system of the Papuan language Bauzi.

We also found that in order for the color “language” used by these neural networks to be an optimal solution, it must use discrete symbols rather than continuous sounds. This leads to a fascinating speculation about how we communicate. Is it possible that our languages can be optimally structured only if they are made up of discrete symbols rather than, say, continuous whistling?

 

How it works:

We built two neural networks, a Speaker and a Listener, and tasked them with playing the “communication game” illustrated below. In each round of the game, the Speaker sees one color chip from a continuous color space and then produces a symbol (which can be considered a “word”). The Listener sees the same color chip but also a different one, known as a distractor.

Read More  Google Cloud launches Optimization AI: Cloud Fleet Routing API To Help Customers Make Route Planning Easier
This graphic shows a successful round of the communication game. Based on a given color chip, the Speaker neural network selects a word (in this case, “blap”) from its vocabulary. The Listener neural network receives the selected word, and must decide which color sample it refers to. In this figure, the Listener correctly chooses the chip in position one.

The Listener receives the word produced by the Speaker and then tries to point to the correct color chip. Initially, the Speaker produces words at random, but eventually these naturally come to denote areas of the color space. We repeated this experiment many times while varying the difficulty of the task by making target and distractor chips more similar or less so. These variations produced a number of different color-naming “vocabularies.”

At the end of training, we analyzed these vocabularies and consistently found that the neural networks developed color terms with properties similar to those of human languages. In particular, when organizing the resulting systems according to quantitative measures of complexity and accuracy—as we do in the chart below—we find that the distribution of the neural-network languages is virtually identical to that of real human languages. Moreover, both types of languages are near the boundary that formally defines the set of possible optimal balances between complexity and accuracy (the black line in the figure).

This chart shows color-naming systems created by human languages (shown in blue) and by neural networks (shown in orange). The black curve defines the theoretical limit on accuracy given complexity, as computed in “Efficient compression in color naming and its evolution.” Both human languages and neural network color-naming systems achieve near-optimal efficiency.

In further experiments, we removed various components of the simulation. We found that, crucially, when we allowed neural networks to communicate through continuous symbols instead of discrete ones, the optimal trade-off between complexity and accuracy no longer emerged. The networks still succeeded at the communication game, but their systems became highly inefficient.

 

Why it matters:

Language is perhaps humanity’s most unique feature, but we still have a poor understanding of many of its core properties. Our study shows that advanced AI models, such as the ones developed at Facebook, are useful not only for practical applications, but also as experimental tools to answer scientific questions about human language (and cognition in general).

Read More  Using AI To Help Health Experts Address The COVID-19 Pandemic

Recent research in linguistics and cognitive science points to the fact that language is a highly efficient system—but how did it evolve to that state, and why? By studying and dissecting computational models that mimic natural behavior, as in our research, we can shed light on the precise conditions under which such an efficient communication system is likely to arise in nature.

The results are also exciting from the perspective of building AI systems that are able to communicate with us through natural language, as it shows that neural networks trained to collaborate to accomplish a common task can develop communication systems that share core properties of human language.

 

Read the full paper:

Communicating artificial neural networks develop efficient color-naming systems

Written By Marco Baroni, Research Scientist | Rahma Chaabouni, Research Assistant | Evgeny Kharitonov, Research Engineer | Emmanuel Dupoux, Research Scientist
Source Facebook AI Research


For enquiries, product placements, sponsorships, and collaborations, connect with us at [email protected]. We'd love to hear from you!

Our humans need coffee too! Your support is highly appreciated, thank you!

liwaiwai.com

Related Topics
  • Colors
  • Facebook AI
  • Facebook AI Research
You May Also Like
View Post
  • Artificial Intelligence
  • Engineering
  • Technology

AI-Driven Tool Makes It Easy To Personalize 3D-Printable Models

  • September 22, 2023
View Post
  • Artificial Intelligence
  • Data

Applying Generative AI To Product Design With BigQuery DataFrames

  • September 21, 2023
View Post
  • Artificial Intelligence
  • Platforms

Combining AI With A Trusted Data Approach On IBM Power To Fuel Business Outcomes

  • September 21, 2023
Microsoft and Adobe
View Post
  • Artificial Intelligence
  • Machine Learning
  • Platforms

Microsoft And Adobe Partner To Deliver Cost Savings And Business Benefits

  • September 21, 2023
View Post
  • Artificial Intelligence
  • Technology

Huawei Connect 2023: Accelerating Intelligence For Shared Success

  • September 20, 2023
View Post
  • Artificial Intelligence
  • Engineering
  • Platforms
  • Tools

Document AI Workbench Is Now Powered By Generative AI To Structure Document Data Faster

  • September 15, 2023
Data
View Post
  • Artificial Intelligence
  • Machine Learning
  • Technology

UK Space Sector Has Sights Set On Artificial Intelligence And Machine Learning Professionals

  • September 15, 2023
Intel Innovation
View Post
  • Artificial Intelligence
  • Technology

Intel Innovation 2023

  • September 15, 2023
A Field Guide To A.I.
Navigate the complexities of Artificial Intelligence and unlock new perspectives in this must-have guide.
Now available in print and ebook.

charity-water



Stay Connected!
LATEST
  • 1
    AI-Driven Tool Makes It Easy To Personalize 3D-Printable Models
    • September 22, 2023
  • 2
    Applying Generative AI To Product Design With BigQuery DataFrames
    • September 21, 2023
  • 3
    Combining AI With A Trusted Data Approach On IBM Power To Fuel Business Outcomes
    • September 21, 2023
  • Microsoft and Adobe 4
    Microsoft And Adobe Partner To Deliver Cost Savings And Business Benefits
    • September 21, 2023
  • 5
    Huawei Connect 2023: Accelerating Intelligence For Shared Success
    • September 20, 2023
  • 6
    Document AI Workbench Is Now Powered By Generative AI To Structure Document Data Faster
    • September 15, 2023
  • Data 7
    UK Space Sector Has Sights Set On Artificial Intelligence And Machine Learning Professionals
    • September 15, 2023
  • Intel Innovation 8
    Intel Innovation 2023
    • September 15, 2023
  • 9
    Introducing OpenAI Dublin
    • September 14, 2023
  • 10
    Microsoft And Oracle Expand Partnership To Deliver Oracle Database Services On Oracle Cloud Infrastructure In Microsoft Azure
    • September 14, 2023

about
About
Hello World!

We are liwaiwai.com. Created by programmers for programmers.

Our site aims to provide materials, guides, programming how-tos, and resources relating to artificial intelligence, machine learning and the likes.

We would like to hear from you.

If you have any questions, enquiries or would like to sponsor content, kindly reach out to us at:

[email protected]

Live long & prosper!
Most Popular
  • 1
    Real-Time Ubuntu Is Now Available In AWS Marketplace
    • September 12, 2023
  • 2
    IBM Brings Watsonx To ESPN Fantasy Football With New Waiver Grades And Trade Grades
    • September 13, 2023
  • 3
    IBM Announced As A Sponsor Of 2023 U.N. Climate Change Conference (COP28)
    • September 13, 2023
  • 4
    NASA Shares Unidentified Anomalous Phenomena Independent Study Report
    • September 14, 2023
  • 5
    Bristol Set To Host UK’s Most Powerful Supercomputer To Turbocharge AI Innovation
    • September 13, 2023
  • /
  • Artificial Intelligence
  • Explore
  • About
  • Contact Us

Input your search keywords and press Enter.