• About
  • Advertise
  • Privacy & Policy
  • Contact
Saturday, September 23, 2023
Earth-News
  • Home
  • Business
  • Entertainment
    Ticketmaster Acknowledges ‘Far More Registered Fans Than Tickets Available’ to Olivia Rodrigo Tour As Would-Be Attendees Lament Sky-High Prices

    Ticketmaster Acknowledges ‘Far More Registered Fans Than Tickets Available’ to Olivia Rodrigo Tour As Would-Be Attendees Lament Sky-High Prices

    Spotify’s Rumored ‘Supremium’ Tier Will Cost $19.99 Per Month, Include HiFi, and Offer ‘Advanced Mixing Tools,’ Code Suggests

    Spotify’s Rumored ‘Supremium’ Tier Will Cost $19.99 Per Month, Include HiFi, and Offer ‘Advanced Mixing Tools,’ Code Suggests

    Peso Pluma Cancels Mexican Concerts Following Cartel Death Threats

    Peso Pluma Cancels Mexican Concerts Following Cartel Death Threats

    YouTube Introduces Suite of AI-Powered Creation Tools

    YouTube Introduces Suite of AI-Powered Creation Tools

    Lizzo Faces Second Lawsuit Over Tour Work Environment — Allegations of Sexual Harassment, Disability Discrimination, Assault, and More

    Lizzo Faces Second Lawsuit Over Tour Work Environment — Allegations of Sexual Harassment, Disability Discrimination, Assault, and More

    A Bride Asks Groom and Guests to Wear Blindfolds as She Walks Down the Aisle, HERE’S WHY

    A Bride Asks Groom and Guests to Wear Blindfolds as She Walks Down the Aisle, HERE’S WHY

  • General
  • Health
  • News
    September Market Trends Reports drills down into oil and gas sales, plus more

    September Market Trends Reports drills down into oil and gas sales, plus more

    National Youth Games: Delta athletes urged to win 7th edition as gift to Gov. Oborevwori

    National Youth Games: Delta athletes urged to win 7th edition as gift to Gov. Oborevwori

    Benue govt. distributes relief materials to IDPs

    Benue govt. distributes relief materials to IDPs

    Police begin search for missing Ekiti varsity female undergraduate

    Police begin search for missing Ekiti varsity female undergraduate

    Army commander charges soldiers to remain disciplined, professional

    Army commander charges soldiers to remain disciplined, professional

    My goal now is to help Tinubu to succeed: Yahaya Bello

    My goal now is to help Tinubu to succeed: Yahaya Bello

    Trending Tags

    • Trump Inauguration
    • United Stated
    • White House
    • Market Stories
    • Election Results
  • Science
  • Sports
  • Tech
    Access Bank fails to double profits in H1 2023, despite 52% growth

    Access Bank fails to double profits in H1 2023, despite 52% growth

    A Somali-based bootcamp is teaching code to young people in native languages

    A Somali-based bootcamp is teaching code to young people in native languages

    New SASSA SRD contact channels for quick help

    New SASSA SRD contact channels for quick help

    Even the most popular femtech apps are still leaving African women behind

    Even the most popular femtech apps are still leaving African women behind

    Latest on using the KPLC self service 2023

    Latest on using the KPLC self service 2023

    Meituan Delivery Takes Four Months to Expand From Kowloon to Hong Kong Island

    Meituan Delivery Takes Four Months to Expand From Kowloon to Hong Kong Island

    Trending Tags

    • Nintendo Switch
    • CES 2017
    • Playstation 4 Pro
    • Mark Zuckerberg
No Result
View All Result
  • Home
  • Business
  • Entertainment
    Ticketmaster Acknowledges ‘Far More Registered Fans Than Tickets Available’ to Olivia Rodrigo Tour As Would-Be Attendees Lament Sky-High Prices

    Ticketmaster Acknowledges ‘Far More Registered Fans Than Tickets Available’ to Olivia Rodrigo Tour As Would-Be Attendees Lament Sky-High Prices

    Spotify’s Rumored ‘Supremium’ Tier Will Cost $19.99 Per Month, Include HiFi, and Offer ‘Advanced Mixing Tools,’ Code Suggests

    Spotify’s Rumored ‘Supremium’ Tier Will Cost $19.99 Per Month, Include HiFi, and Offer ‘Advanced Mixing Tools,’ Code Suggests

    Peso Pluma Cancels Mexican Concerts Following Cartel Death Threats

    Peso Pluma Cancels Mexican Concerts Following Cartel Death Threats

    YouTube Introduces Suite of AI-Powered Creation Tools

    YouTube Introduces Suite of AI-Powered Creation Tools

    Lizzo Faces Second Lawsuit Over Tour Work Environment — Allegations of Sexual Harassment, Disability Discrimination, Assault, and More

    Lizzo Faces Second Lawsuit Over Tour Work Environment — Allegations of Sexual Harassment, Disability Discrimination, Assault, and More

    A Bride Asks Groom and Guests to Wear Blindfolds as She Walks Down the Aisle, HERE’S WHY

    A Bride Asks Groom and Guests to Wear Blindfolds as She Walks Down the Aisle, HERE’S WHY

  • General
  • Health
  • News
    September Market Trends Reports drills down into oil and gas sales, plus more

    September Market Trends Reports drills down into oil and gas sales, plus more

    National Youth Games: Delta athletes urged to win 7th edition as gift to Gov. Oborevwori

    National Youth Games: Delta athletes urged to win 7th edition as gift to Gov. Oborevwori

    Benue govt. distributes relief materials to IDPs

    Benue govt. distributes relief materials to IDPs

    Police begin search for missing Ekiti varsity female undergraduate

    Police begin search for missing Ekiti varsity female undergraduate

    Army commander charges soldiers to remain disciplined, professional

    Army commander charges soldiers to remain disciplined, professional

    My goal now is to help Tinubu to succeed: Yahaya Bello

    My goal now is to help Tinubu to succeed: Yahaya Bello

    Trending Tags

    • Trump Inauguration
    • United Stated
    • White House
    • Market Stories
    • Election Results
  • Science
  • Sports
  • Tech
    Access Bank fails to double profits in H1 2023, despite 52% growth

    Access Bank fails to double profits in H1 2023, despite 52% growth

    A Somali-based bootcamp is teaching code to young people in native languages

    A Somali-based bootcamp is teaching code to young people in native languages

    New SASSA SRD contact channels for quick help

    New SASSA SRD contact channels for quick help

    Even the most popular femtech apps are still leaving African women behind

    Even the most popular femtech apps are still leaving African women behind

    Latest on using the KPLC self service 2023

    Latest on using the KPLC self service 2023

    Meituan Delivery Takes Four Months to Expand From Kowloon to Hong Kong Island

    Meituan Delivery Takes Four Months to Expand From Kowloon to Hong Kong Island

    Trending Tags

    • Nintendo Switch
    • CES 2017
    • Playstation 4 Pro
    • Mark Zuckerberg
No Result
View All Result
Earth-News
No Result
View All Result
Home Science

The Physical Process That Powers a New Type of Generative AI

September 19, 2023
in Science
The Physical Process That Powers a New Type of Generative AI
Share on FacebookShare on Twitter

Nash Weerasekera for Quanta Magazine

Table of Contents

  • Introduction
  • Introduction
  • Introduction

Introduction

The tools of artificial intelligence — neural networks in particular — have been good to physicists. For years, this technology has helped researchers reconstruct particle trajectories in accelerator experiments, search for evidence of new particles, and detect gravitational waves and exoplanets. While AI tools can clearly do a lot for physicists, the question now, according to Max Tegmark, a physicist at the Massachusetts Institute of Technology, is: “Can we give anything back?”

Tegmark believes that his physicist peers can make significant contributions to the science of AI, and he has made this his top research priority. One way physicists could help advance AI technology, he said, would be to replace the “black box” algorithms of neural networks, whose workings are largely inscrutable, with well-understood equations of physical processes.

The idea is not brand-new. Generative AI models based on diffusion — the process that, for instance, causes milk poured into a cup of coffee to spread uniformly — first emerged in 2015, and the quality of the images they generate has improved significantly since then. That technology powers popular image-producing software such as DALL·E 2 and Midjourney. Now, Tegmark and his colleagues are learning whether other physics-inspired generative models might work as well as diffusion-based models, or even better.

Late last year, Tegmark’s team introduced a promising new method of producing images called the Poisson flow generative model (PFGM). In it, data is represented by charged particles, which combine to create an electric field whose properties depend on the distribution of the charges at any given moment. It’s called a Poisson flow model because the movement of charges is governed by the Poisson equation, which derives from the principle stating that the electrostatic force between two charges varies inversely with the square of the distance between them (similar to the formulation of Newtonian gravity).

That physical process is at the heart of PFGM. “Our model can be characterized almost completely by the strength and direction of the electric field at every point in space,” said Yilun Xu, a graduate student at MIT and co-author of the paper. “What the neural network learns during the training process is how to estimate that electric field.” And in so doing, it can learn to create images because an image in this model can be succinctly described by an electric field.

Yilun Xu stands outdoors wearing a white shirt

Yilun Xu helped establish a new way for neural networks to create images by exploiting the physical process whereby charges particles produce an electric field.

Tianyuan Zhang

Introduction

PFGM can create images of the same quality as those produced by diffusion-based approaches and do so 10 to 20 times faster. “It utilizes a physical construct, the electric field, in a way we’ve never seen before,” said Hananel Hazan, a computer scientist at Tufts University. “That opens the door to the possibility of other physical phenomena being harnessed to improve our neural networks.”

Diffusion and Poisson flow models have a lot in common, besides being based on equations imported from physics. During training, a diffusion model designed for image generation typically starts with a picture — a dog, let’s say — and then adds visual noise, altering each pixel in a random way until its features become thoroughly shrouded (though not completely eliminated). The model then attempts to reverse the process and generate a dog that’s close to the original. Once trained, the model can successfully create dogs — and other imagery — starting from a seemingly blank canvas.

Poisson flow models operate in much the same way. During training, there’s a forward process, which involves adding noise, incrementally, to a once-sharp image, and a reverse process in which the model attempts to remove that noise, step by step, until the initial version is mostly recovered. As with diffusion-based generation, the system eventually learns to make images it never saw in training.

But the physics underlying Poisson models is entirely different. Diffusion is driven by thermodynamic forces, whereas Poisson flow is driven by electrostatic forces. The latter represents a detailed image using an arrangement of charges that can create a very complicated electric field. That field, however, causes the charges to spread more evenly over time — just as milk naturally disperses in a cup of coffee. The result is that the field itself becomes simpler and more uniform. But this noise-ridden uniform field is not a complete blank slate; it still contains the seeds of information from which images can be readily assembled.

In early 2023, the team upgraded their Poisson model, extending it to encompass an entire family of models. The augmented version, PFGM++, includes a new parameter, D, which allows researchers to adjust the dimensionality of the system. This can make a big difference: In familiar three-dimensional space, the strength of the electric field produced by a charge is inversely related to the square of the distance from that charge. But in four dimensions, the field strength follows an inverse cube law. And for every dimension of space, and every value of D, that relation is somewhat different.

Ziming Liu stands in front of a fountain wearing a blue striped shirt and a baseball cap.

Ziming Liu was also part of the team that expanded PFGM to include multiple possible dimensions, which allows researchers to fine tune a neural network’s robustness and its ease of training.

Wenting Gong

Introduction

That single innovation gave Poisson flow models far greater variability, with the extreme cases offering different benefits. When D is low, for example, the model is more robust, meaning it is more tolerant of the errors made in estimating the electric field. “The model can’t predict the electric field perfectly,” said Ziming Liu, another graduate student at MIT and co-author of both papers. “There’s always some deviation. But robustness means that even if your estimation error is high, you can still generate good images.” So you may not end up with the dog of your dreams, but you’ll still end up with something resembling a dog.

At the other extreme, when D is high, the neural network becomes easier to train, requiring less data to master its artistic skills. The exact reason isn’t easy to explain, but it owes to the fact that when there are more dimensions, the model has fewer electric fields to keep track of — and hence less data to assimilate.

The enhanced model, PFGM++, “gives you the flexibility to interpolate between those two extremes,” said Rose Yu, a computer scientist at the University of California, San Diego.

And somewhere within this range lies an ideal value for D that strikes the right balance between robustness and ease of training, said Xu. “One goal of future work will be to figure out a systematic way of finding that sweet spot, so we can select the best possible D for a given situation without resorting to trial and error.”

Another goal for the MIT researchers involves finding more physical processes that can provide the basis for new families of generative models. Through a project called GenPhys, the team has already identified one promising candidate: the Yukawa potential, which relates to the weak nuclear force. “It’s different from Poisson flow and diffusion models, where the number of particles is always conserved,” Liu said. “The Yukawa potential allows you to annihilate particles or split a particle into two. Such a model might, for instance, simulate biological systems where the number of cells does not have to stay the same.”

This may be a fruitful line of inquiry, Yu said. “It could lead to new algorithms and new generative models with potential applications extending beyond image generation.”

And PFGM++ alone has already exceeded its inventors’ original expectations. They did not realize at first that when D is set to infinity, their amped-up Poisson flow model becomes indistinguishable from a diffusion model. Liu discovered this in calculations he carried out earlier this year.

Mert Pilanci, a computer scientist at Stanford University, considers this “unification” the most important result stemming from the MIT group’s work. “The PFGM++ paper,” he said, “reveals that both of these models are part of a broader class, [which] raises an intriguing question: Might there be other physical models for generative AI awaiting discovery, hinting at an even grander unification?”

>>> Read full article>>>
Copyright for syndicated content belongs to the linked Source : Quanta Magazine – https://www.quantamagazine.org/new-physics-inspired-generative-ai-exceeds-expectations-20230919/

Tags: Physicalprocessscience
Previous Post

How National Petroleum Company, NNPCL Failed To Remit Over $6.9billion Under Ex-President, Buhari – Nigerian Transparency Agency, NEITI Report

Next Post

Caleb Williams, USC vs. Shedeur, Deion Sanders, Colorado Game Time Set for Week 5

Save $45 on these open-ear conduction stereo wireless headphones

Save $45 on these open-ear conduction stereo wireless headphones

September 23, 2023
In photos: Airbus Helicopters’ fancy flying machine, the H160

In photos: Airbus Helicopters’ fancy flying machine, the H160

September 23, 2023
The best workout apps for all kinds of exercisers

The best workout apps for all kinds of exercisers

September 23, 2023
The best cheap Android phones of 2023

The best cheap Android phones of 2023

September 23, 2023
Nature generates more data than the internet … for now

Nature generates more data than the internet … for now

September 23, 2023
Vinci/McAlpine JV to start £105m NHS rehabilitation centre

Vinci/McAlpine JV to start £105m NHS rehabilitation centre

September 23, 2023
Three giant lab buildings approved at £700m Oxford R&D district

Three giant lab buildings approved at £700m Oxford R&D district

September 23, 2023
Purdue University to Launch Trimble Technology Lab

Purdue University to Launch Trimble Technology Lab

September 23, 2023
Fantasy Alert: Browns’ Kareem Hunt to Play vs. Titans After Nick Chubb’s Knee Injury

Fantasy Alert: Browns’ Kareem Hunt to Play vs. Titans After Nick Chubb’s Knee Injury

September 23, 2023
Jets’ Aaron Rodgers Updates ‘Tough’ Achilles Rehab, Says Injury Is ‘Disappointing’

Jets’ Aaron Rodgers Updates ‘Tough’ Achilles Rehab, Says Injury Is ‘Disappointing’

September 23, 2023
Partenaires
afric.info
europ.info
usa-news
lesmeilleureschaussures.fr
goodsforyoutoday.com
looktopbeauty.com
keto-diet.biz
soccernews.info
nba-news.net
sportsprblog.com compar.biz
the-best.top
bestchoices.biz
expert-plus.fr
travel-mag.info
pksportsnews.com
news-sports.org

Categories

Archives

September 2023
M T W T F S S
 123
45678910
11121314151617
18192021222324
252627282930  
« Aug    
Earth-News.info

The Earth News is an independent English-language daily published Website from all around the World News

Browse by Category

  • Business (3,369)
  • Entertainment (3,417)
  • General (2,455)
  • Health (1,637)
  • News (3,866)
  • Science (2,657)
  • Sports (3,575)
  • Tech (2,617)

Recent News

Save $45 on these open-ear conduction stereo wireless headphones

Save $45 on these open-ear conduction stereo wireless headphones

September 23, 2023
In photos: Airbus Helicopters’ fancy flying machine, the H160

In photos: Airbus Helicopters’ fancy flying machine, the H160

September 23, 2023
  • About
  • Advertise
  • Privacy & Policy
  • Contact

© 2023 earth-news.info

No Result
View All Result

© 2023 earth-news.info

Go to mobile version

The Physical Process That Powers a New Type of Generative AI- https://news7.asia/   https://www.animaleries.info   https://www.comptoirdubagage.biz/   https://www.wa-news.com/   https://www.magasinjouet.net/   https://teenoi.net   https://paschers.info   https://www.1nfo.net   -/- J’ai encore menti !   Bensimon femme Sport Bag Sac bandouliere Orange (Coquelicot)   Asus ExpertCenter PB63: 1.35 liter mini PC debuts with support for 65 W Intel processors   Wimbledon 2023: British number one Cameron Norrie beats Tomas Machac to reach round two   Douyin Boosts Self-Operated E-Commerce with Launch of ‘Imported Supermarket’   -*-$$Antoine Dupont blessé : le capitaine du XV de France a été opéré et va pouvoir rejoindre les Bleus   Lampe de Scène, Lumière Fête 9W 9 couleurs Éclairage Soirée Boule Disco Avec Bluetooth Président sans fil de connexion…   Honte à l’“anti-rugby” de l’Angleterre, et vive les flamboyants “petits poucets”   Stormsure Stormproof Durable Hydrofuge (spray étanche) – 1L   Meilleurs choix d’appareils photo : Olympus OM-D E-M10 Mark II   $$* James Betterave Blanche It Betterave Organique 1L De Jus   Secret des Chefs Arome Naturel Grenadine 50 ml – Lot de 2   The Physical Process That Powers a New Type of Generative AI *The Physical Process That Powers a New Type of Generative AI