Close Menu
Ztoog
    What's Hot
    Gadgets

    Google is killing Play Movies & TV, will only have three video stores left

    AI

    CMU Researchers Introduce VisualWebArena: An AI Benchmark Designed to Evaluate the Performance of Multimodal Web Agents on Realistic and Visually Stimulating Challenges

    Gadgets

    Convert food scraps to nutrient-rich fertilizer from home with this sleek composter, now over $200 off

    Important Pages:
    • About Us
    • Contact us
    • Privacy Policy
    • Terms & Conditions
    Facebook X (Twitter) Instagram Pinterest
    Facebook X (Twitter) Instagram Pinterest
    Ztoog
    • Home
    • The Future

      JD Vance and President Trump’s Sons Hype Bitcoin at Las Vegas Conference

      AI may already be shrinking entry-level jobs in tech, new research suggests

      Today’s NYT Strands Hints, Answer and Help for May 26 #449

      LiberNovo Omni: The World’s First Dynamic Ergonomic Chair

      Common Security Mistakes Made By Businesses and How to Avoid Them

    • Technology

      Gemini in Google Drive can now help you skip watching that painfully long Zoom meeting

      Apple iPhone exports from China to the US fall 76% as India output surges

      Today’s NYT Wordle Hints, Answer and Help for May 26, #1437

      5 Skills Kids (and Adults) Need in an AI World – O’Reilly

      How To Come Back After A Layoff

    • Gadgets

      8 Best Vegan Meal Delivery Services and Kits (2025), Tested and Reviewed

      Google Home is getting deeper Gemini integration and a new widget

      Google Announces AI Ultra Subscription Plan With Premium Features

      Google shows off Android XR-based glasses, announces Warby Parker team-up

      The market’s down, but this OpenAI for the stock market can help you trade up

    • Mobile

      Microsoft is done being subtle – this new tool screams “upgrade now”

      Wallpaper Wednesday: Android wallpapers 2025-05-28

      Google can make smart glasses accessible with Warby Parker, Gentle Monster deals

      vivo T4 Ultra specs leak

      Forget screens: more details emerge on the mysterious Jony Ive + OpenAI device

    • Science

      Do we have free will? Quantum experiments may soon reveal the answer

      Was Planet Nine exiled from the solar system as a baby?

      How farmers can help rescue water-loving birds

      A trip to the farm where loofahs grow on vines

      AI Is Eating Data Center Power Demand—and It’s Only Getting Worse

    • AI

      The AI Hype Index: College students are hooked on ChatGPT

      Learning how to predict rare kinds of failures | Ztoog

      Anthropic’s new hybrid AI model can work on tasks autonomously for hours at a time

      AI learns how vision and sound are connected, without human intervention | Ztoog

      How AI is introducing errors into courtrooms

    • Crypto

      GameStop bought $500 million of bitcoin

      CoinW Teams Up with Superteam Europe to Conclude Solana Hackathon and Accelerate Web3 Innovation in Europe

      Ethereum Net Flows Turn Negative As Bulls Push For $3,500

      Bitcoin’s Power Compared To Nuclear Reactor By Brazilian Business Leader

      Senate advances GENIUS Act after cloture vote passes

    Ztoog
    Home » Probabilistic AI that knows how well it’s working | Ztoog
    AI

    Probabilistic AI that knows how well it’s working | Ztoog

    Facebook Twitter Pinterest WhatsApp
    Probabilistic AI that knows how well it’s working | Ztoog
    Share
    Facebook Twitter LinkedIn Pinterest WhatsApp

    Despite their monumental dimension and energy, at the moment’s synthetic intelligence programs routinely fail to differentiate between hallucination and actuality. Autonomous driving programs can fail to understand pedestrians and emergency automobiles proper in entrance of them, with deadly penalties. Conversational AI programs confidently make up info and, after coaching by way of reinforcement studying, usually fail to present correct estimates of their very own uncertainty.

    Working collectively, researchers from MIT and the University of California at Berkeley have developed a brand new technique for constructing refined AI inference algorithms that concurrently generate collections of possible explanations for knowledge, and precisely estimate the standard of those explanations.

    The new technique is predicated on a mathematical strategy known as sequential Monte Carlo (SMC). SMC algorithms are a longtime set of algorithms that have been extensively used for uncertainty-calibrated AI, by proposing possible explanations of knowledge and monitoring how doubtless or unlikely the proposed explanations appear at any time when given extra info. But SMC is just too simplistic for complicated duties. The essential subject is that one of many central steps within the algorithm — the step of really arising with guesses for possible explanations (earlier than the opposite step of monitoring how doubtless completely different hypotheses appear relative to at least one one other) — needed to be quite simple. In difficult utility areas, taking a look at knowledge and arising with believable guesses of what’s happening could be a difficult drawback in its personal proper. In self driving, for instance, this requires trying on the video knowledge from a self-driving automotive’s cameras, figuring out vehicles and pedestrians on the highway, and guessing possible movement paths of pedestrians at the moment hidden from view.  Making believable guesses from uncooked knowledge can require refined algorithms that common SMC can’t assist.

    That’s the place the brand new technique, SMC with probabilistic program proposals (SMCP3), is available in. SMCP3 makes it doable to make use of smarter methods of guessing possible explanations of knowledge, to replace these proposed explanations in gentle of latest info, and to estimate the standard of those explanations that had been proposed in refined methods. SMCP3 does this by making it doable to make use of any probabilistic program — any pc program that can be allowed to make random selections — as a technique for proposing (that is, intelligently guessing) explanations of knowledge. Previous variations of SMC solely allowed using quite simple methods, so easy that one might calculate the precise likelihood of any guess. This restriction made it troublesome to make use of guessing procedures with a number of phases.

    The researchers’ SMCP3 paper exhibits that by utilizing extra refined proposal procedures, SMCP3 can enhance the accuracy of AI programs for monitoring 3D objects and analyzing knowledge, and likewise enhance the accuracy of the algorithms’ personal estimates of how doubtless the info is. Previous analysis by MIT and others has proven that these estimates can be utilized to deduce how precisely an inference algorithm is explaining knowledge, relative to an idealized Bayesian reasoner.

    George Matheos, co-first creator of the paper (and an incoming MIT electrical engineering and pc science [EECS] PhD pupil), says he’s most excited by SMCP3’s potential to make it sensible to make use of well-understood, uncertainty-calibrated algorithms in difficult drawback settings the place older variations of SMC didn’t work.

    “Today, we have lots of new algorithms, many based on deep neural networks, which can propose what might be going on in the world, in light of data, in all sorts of problem areas. But often, these algorithms are not really uncertainty-calibrated. They just output one idea of what might be going on in the world, and it’s not clear whether that’s the only plausible explanation or if there are others — or even if that’s a good explanation in the first place! But with SMCP3, I think it will be possible to use many more of these smart but hard-to-trust algorithms to build algorithms that are uncertainty-calibrated. As we use ‘artificial intelligence’ systems to make decisions in more and more areas of life, having systems we can trust, which are aware of their uncertainty, will be crucial for reliability and safety.”

    Vikash Mansinghka, senior creator of the paper, provides, “The first digital computer systems had been constructed to run Monte Carlo strategies, and they’re a number of the most generally used methods in computing and in synthetic intelligence. But because the starting, Monte Carlo strategies have been troublesome to design and implement: the mathematics needed to be derived by hand, and there have been numerous delicate mathematical restrictions that customers had to pay attention to. SMCP3 concurrently automates the arduous math, and expands the house of designs. We’ve already used it to think about new AI algorithms that we could not have designed earlier than.”

    Other authors of the paper embrace co-first creator Alex Lew (an MIT EECS PhD pupil); MIT EECS PhD college students Nishad Gothoskar, Matin Ghavamizadeh, and Tan Zhi-Xuan; and Stuart Russell, professor at UC Berkeley. The work was offered on the AISTATS convention in Valencia, Spain, in April.

    Share. Facebook Twitter Pinterest LinkedIn WhatsApp

    Related Posts

    AI

    The AI Hype Index: College students are hooked on ChatGPT

    AI

    Learning how to predict rare kinds of failures | Ztoog

    AI

    Anthropic’s new hybrid AI model can work on tasks autonomously for hours at a time

    AI

    AI learns how vision and sound are connected, without human intervention | Ztoog

    AI

    How AI is introducing errors into courtrooms

    AI

    With AI, researchers predict the location of virtually any protein within a human cell | Ztoog

    AI

    Google DeepMind’s new AI agent cracks real-world problems better than humans can

    AI

    Study shows vision-language models can’t handle queries with negation words | Ztoog

    Leave A Reply Cancel Reply

    Follow Us
    • Facebook
    • Twitter
    • Pinterest
    • Instagram
    Top Posts
    AI

    Researchers from Yale and Google Introduce HyperAttention: An Approximate Attention Mechanism Accelerating Large Language Models for Efficient Long-Range Sequence Processing

    The fast development of huge language fashions has paved the best way for breakthroughs in…

    Crypto

    ERC-404 Euphoria Push Ethereum Gas Fees To 8 Month High

    The new ERC-404 tokens have swiftly taken the highlight, dominating the cryptocurrency market and constantly…

    Mobile

    Google One passes landmark subscribers milestone

    Edgar Cervantes / Android AuthorityTL;DR Google One simply handed 100 million subscribers. The Friday morning…

    Technology

    Beyond light pollution: Starlink satellites are also interfering with radio signals

    Why it issues: Elon Musk’s ever-expanding community of Starlink web satellites is more and more…

    The Future

    Netflix ends a three-year legal dispute over Squid Game traffic

    The lawsuits began as a result of SK Broadband needed Netflix to assist cowl the…

    Our Picks
    Crypto

    4-Year Cycle And Elliot Wave

    Technology

    Dealroom: in 2023, the combined enterprise value of Spanish startups surpassed €100B, and they raised €2.2B across 850+ funding rounds (Anna Heim/Ztoog)

    Science

    Geminid meteor shower 2023: How to see the spectacular show late tonight

    Categories
    • AI (1,492)
    • Crypto (1,753)
    • Gadgets (1,804)
    • Mobile (1,850)
    • Science (1,865)
    • Technology (1,801)
    • The Future (1,647)
    Most Popular
    The Future

    Clibrain’s Lince: The LLM That Understands Spanish Like a Native Speaker

    Technology

    Timesplitters re-release on the way, if ratings board listing is right

    Crypto

    SEC settles with former Coinbase employee over insider trading charges

    Ztoog
    Facebook X (Twitter) Instagram Pinterest
    • Home
    • About Us
    • Contact us
    • Privacy Policy
    • Terms & Conditions
    © 2025 Ztoog.

    Type above and press Enter to search. Press Esc to cancel.