• Skip to main content
  • Skip to primary sidebar

Biz Builder Mike

You can't sail Today's boat on Yesterdays wind - Michael Noel

  • Tokenomics is not Economics – Digital CX -The Digital Transformation
  • Resume / CV – Michael Noel
  • Contact Us
  • Featured
You are here: Home / AI / New method for comparing neural networks exposes how artificial intelligence works

Sep 14 2022

New method for comparing neural networks exposes how artificial intelligence works

A team at Los Alamos National Laboratory has developed a novel approach for comparing neural networks that looks within the “black box” of artificial intelligence to help researchers understand neural network behavior. Neural networks recognize patterns in datasets; they are used everywhere in society, in applications such as virtual assistants, facial recognition systems and self-driving cars.

“The artificial intelligence research community doesn’t necessarily have a complete understanding of what neural networks are doing; they give us good results, but we don’t know how or why,” said Haydn Jones, a researcher in the Advanced Research in Cyber Systems group at Los Alamos. “Our new method does a better job of comparing neural networks, which is a crucial step toward better understanding the mathematics behind AI.”

Jones is the lead author of the paper “If You’ve Trained One You’ve Trained Them All: Inter-Architecture Similarity Increases With Robustness,” which was presented recently at the Conference on Uncertainty in Artificial Intelligence. In addition to studying network similarity, the paper is a crucial step toward characterizing the behavior of robust neural networks.

Neural networks are high performance, but fragile. For example, self-driving cars use neural networks to detect signs. When conditions are ideal, they do this quite well. However, the smallest aberration — such as a sticker on a stop sign — can cause the neural network to misidentify the sign and never stop.

To improve neural networks, researchers are looking at ways to improve network robustness. One state-of-the-art approach involves “attacking” networks during their training process. Researchers intentionally introduce aberrations and train the AI to ignore them. This process is called adversarial training and essentially makes it harder to fool the networks.

Jones, Los Alamos collaborators Jacob Springer and Garrett Kenyon, and Jones’ mentor Juston Moore, applied their new metric of network similarity to adversarially trained neural networks, and found, surprisingly, that adversarial training causes neural networks in the computer vision domain to converge to very similar data representations, regardless of network architecture, as the magnitude of the attack increases.

“We found that when we train neural networks to be robust against adversarial attacks, they begin to do the same things,” Jones said.

There has been extensive effort in industry and in the academic community searching for the “right architecture” for neural networks, but the Los Alamos team’s findings indicate that the introduction of adversarial training narrows this search space substantially. As a result, the AI research community may not need to spend as much time exploring new architectures, knowing that adversarial training causes diverse architectures to converge to similar solutions.

“By finding that robust neural networks are similar to each other, we’re making it easier to understand how robust AI might really work. We might even be uncovering hints as to how perception occurs in humans and other animals,” Jones said.

Story Source:

Materials provided by DOE/Los Alamos National Laboratory. Note: Content may be edited for style and length.

DON’T MISS A BEAT

Top Stories from around the world, delivered straight to your inbox. Once Weekly.

We don’t spam! Read our privacy policy https://bizbuildermike.com/anti-spam-policy/ for more info.

Check your inbox or spam folder to confirm your subscription.

New method for comparing neural networks exposes how artificial intelligence works Republished from Source https://www.sciencedaily.com/releases/2022/09/220914102256.htm via https://www.sciencedaily.com/rss/computers_math/artificial_intelligence.xml

crowdsourcing week

Written by bizbuildermike · Categorized: AI · Tagged: AI

Primary Sidebar

https://youtu.be/Qvad1CQ9WOM

Blockchain Weekly Rebooted –

During the Blockchain Spring 2016 to 2020 I hosted Blockchain Weekly. Each week I interviewed someone who was doing interesting things in the blockchain space. At one time we had 29k subscribers and we were consistently getting over 15k views a week on the channel. All of that went away during the lockdown, including the Gmail address that controlled that channel. Recently, I found some of the original videos on some old hard drives. So I’m reposting a few of the relevant ones while I am starting to shoot new Blockchain Weekly Episodes to be aired 1st quarter 2023. Please subscribe to bless the You Tube Algorithm, and allow me to let you know about any updates! Our Sponsor – https://BlockchainConsultants.io

Recent reports indicate that Republican United States Senator Tim Scott, who serves as the ranking member of the Senate Banking Committee, aims to build “a bipartisan regulatory framework” for virtual currencies. Senator Scott is the ranking member of the Senate Banking Committee. In a piece that was published on the 2nd of February by Politico, […]

Search Here

Market Insights

  • Talking to Robots in Real Time
  • Electric-van start-up Arrival to cut half its remaining staff
  • Amazon: ‘Alexa, can you tell me where the money went?’
  • Premier League backs Sorare’s NFT fantasy football game despite crypto crash
  • Slimming down Big Tech
  • Hackers Launder $27 Million in Stolen Ethereum From North Korean
  • Core Scientific seeks to sell $6.6 million in Bitmain coupons
  • Shoshana Zuboff: ‘Privacy has been extinguished. It is now a zombie’
  • 8 Ways to Be More Productive After Taking a Vacation
  • [Review] Poly Studio P5 Web Camera

Tags

AI (195) andrewchen (4) Biz Builder Mike (24) Blockchain (375) Crowd Funding (50) crowdfundinsider (2) entrepreneur (694) eonetwork (28) Front Page Featured (23) MIT AI (72) startupmindset (96) Technology (413) virtual reality (1) youngupstarts (153)
  • Twitter
  • Facebook
  • About Us
  • LinkedIn
  • ANTI-SPAM POLICY
  • Google+
  • API Terms and Conditions
  • RSS
  • Archive Page
  • Biz Builder Mike is all about New World Marketing
  • Cryptocurrency Exchange
  • Digital Millennium Copyright Act (DMCA) Notice
  • DMCA Safe Harbor Explained: Why Your Website Needs a DMCA/Copyright Policy
  • Marketing? Well, how hard can that be?
  • Michael Noel
  • Michael Noel CBP
  • Noels Law of decentralization

Copyright © 2023 · Altitude Pro on Genesis Framework · WordPress · Log in

en English
ar Arabiczh-CN Chinese (Simplified)nl Dutchen Englishtl Filipinofi Finnishfr Frenchde Germanit Italianko Koreanpt Portugueseru Russiansd Sindhies Spanishtr Turkishuz Uzbekyi Yiddishyo Yoruba