TechBriefly
  • Tech
  • Business
  • Crypto
  • Science
  • Geek
  • How to
  • About
    • About TechBriefly
    • Terms and Conditions
    • Privacy Policy
    • Contact Us
    • Languages
      • 中文 (Chinese)
      • Dansk
      • Deutsch
      • Español
      • English
      • Français
      • Nederlands
      • Italiano
      • 日本语 (Japanese)
      • 한국인 (Korean)
      • Norsk
      • Polski
      • Português
      • Pусский (Russian)
      • Suomalainen
      • Svenska
  • FAQ
    • Articles
No Result
View All Result
 Hot Topics:
  • Nvidia
  • Snapchat planets order
  • Replika AI
  • Lookism AI filter
  • Binance WOTD answers (Portfolios)
TechBriefly
No Result
View All Result
Home Tech AI

Can Artificial Intelligence imagine things?

by Barış Selman
16 July 2021
in AI, Tech
Reading Time: 2 mins read
Can Artificial Intelligence imagine things?
Share on FacebookShare on Twitter

Can Artificial Intelligence imagine things? Imagination is a complex process. If we stop to think about the number of elements that can make up an imaginary scenario, it is easier to begin to approach a notion of how profound this mental procedure can be.

A team of researchers from the University of Southern California, USA, presented a project that seeks to endow AI with a similar quality, in order to implement systems capable of creating new concepts based on known elements.

A new system that allows Artificial Intelligence to imagine

At first glance, the idea of training an artificial intelligence system with “human capabilities” may sound strange. However, this has a practical, interesting, and approachable purpose.

The imagination process is generally defined as a creative process in which, based on previously perceived elements, new mental images are constructed. Taking this to the AI plane, a system that masters a good number of drug formulas, for example, could decompose their components and functions, in order to start testing new recipes.

Mechanisms of this kind have been presented before, but limited in their action to a certain context, such as the example just mentioned of drugs. Unlike those, the AI developed by USC researchers can be extrapolated to different applications. This means that in different scenarios, this system should be able to define its own rules and variables, to configure as many combinations of attributes as possible.

Can Artificial Intelligence imagine things?
Can Artificial Intelligence imagine things?

To achieve this versatility, the researchers used a mechanism similar to that used in the generation of deep fakes. Just as in the case of these tricked audiovisual pieces, an algorithm can identify a person’s face and gestures, to emulate them with a digitally replaced face; in the case of this Artificial Intelligence, the system would be able to recognize the components of each scenario analyzed.

In a conversation with his house of studies, student Yunhao Ge, part of the team behind this development, exemplified this process based on the movie Transformers. “It can take the shape of a Megatron car, the color and pose of a yellow Bumblebee car, and the background of New York’s Times Square. The result will be a colored Bumblebee Megatron Car, driving in Times Square, even if this sample was not witnessed during the training session,” he commented.

In the same instance, another member of this team, Professor Laurent Itti, commented that “deep learning has already shown unsurpassed performance and promise in many domains, but too often this has happened through superficial mimicry and without a deeper understanding of the separate attributes that make each object unique,” adding that “this new approach to disentanglement, for the first time, really unleashes a new sense of imagination in AI systems, bringing them closer to human understanding of the world.”

With systems like this, autonomous cars would be able to imagine as many scenarios as possible based on weather and environmental factors, strengthening their safety. And so, as needs compatible with what this system offers are identified, the catalog of possible applications could continue to grow.

Details of this research were made public in a paper entitled “Zero-Shot Synthesis with Group-Supervised Learning“, released at this year’s International Conference on Learning Representations.

Tags: AIartificial intelligencefeaturedtechnology

Related Posts

Diablo 4 Necromancer builds

Best Diablo 4 Necromancer builds to try out

Diablo 4 best builds

Diablo 4 best builds for each class

NVIDIA 535.98: What you need to know

NVIDIA 535.98: What you need to know

Spotify Find Your Flow

Spotify Find Your Flow reimagines the soundtrack for 2023

POPULAR

Binance Word of the Day answers: Crypto Portfolios theme

Binance Word of the Day answers: Bitcoin Fundamentals theme

RCM Loader for Nintendo Switch: What is it, how can you install?

Is there a way to remove Character AI NSFW filters?

What does setting interrogation succeeded mean?

How to fix “no secure boot’ and “DLC assets are damaged” errors on FIFA 23?

Can Chai see your chats?

What is Instagram direct message suggested list order (explained)?

What is Snapchat planets order?

How to play Minecraft Jenny mod?

RSS News Republic

  • 7 best NSFW AI art generators
  • A joke goes viral: How long do idiots live?
  • Elon Musk’s actual height revealed: How tall is he?
  • Hogwarts Legacy: Which ball in Quidditch is the largest?
  • Backbone One PlayStation Android: Specs, price, and release date

RSS Digital Report

  • Using Voice of the Customer for marketing and its benefits
  • Creating estimations for cost and organic traffic for your future SEO endeavors
  • Biggest issues plaguing the blockchain in 2023
  • What is the “Framing Effect” in marketing and how to use it?
  • How does in-house SEO compare to utilizing agencies and how to get started with it?

RSS Latest from LeaderGamer

  • League of Slots Game Collection Review
  • Twitter Spaces – What is Twitter Space and How to Open it?
  • What is Twitter search and how to use it?
  • What is Twitter Trending?
  • Download Twitter – How to Download Twitter?
TechBriefly

© 2021 TechBriefly is a Linkmedya brand.

  • Tech
  • Business
  • Science
  • Geek
  • How to
  • About
  • Privacy
  • Terms
  • Contact
  • FAQ
  • | Network Sites |
  • Digital Report
  • LeaderGamer
  • News Republic

Follow Us

No Result
View All Result
  • Tech
  • Business
  • Crypto
  • Science
  • Geek
  • How to
  • About
    • About TechBriefly
    • Terms and Conditions
    • Privacy Policy
    • Contact Us
    • Languages
      • 中文 (Chinese)
      • Dansk
      • Deutsch
      • Español
      • English
      • Français
      • Nederlands
      • Italiano
      • 日本语 (Japanese)
      • 한국인 (Korean)
      • Norsk
      • Polski
      • Português
      • Pусский (Russian)
      • Suomalainen
      • Svenska
  • FAQ
    • Articles