Algorithm lets independent agents collectively produce a machine-learning model without aggregating data.
Machine learning, in which computers learn new skills by looking for patterns in training data, is the basis of most recent advances in artificial intelligence, from voice-recognition systems to self-parking cars. It’s also the technique that autonomous robots typically use to build models of their environments.
That type of model-building gets complicated, however, in cases in which clusters of robots work as teams. The robots may have gathered information that, collectively, would produce a good model but which, individually, is almost useless. If constraints on power, communication, or computation mean that the robots can’t pool their data at one location, how can they collectively build a model?
At the Uncertainty in Artificial Intelligence conference in July, researchers from MIT’s Laboratory for Information and Decision Systems will answer that question. They present an algorithm in which distributed agents — such as robots exploring a building — collect data and analyze it independently. Pairs of agents, such as robots passing each other in the hall, then exchange analyses.
In experiments involving several different data sets, the researchers’ distributed algorithm actually outperformed a standard algorithm that works on data aggregated at a single location.
The Latest on: Robot learning
[google_news title=”” keyword=”Robot learning” num_posts=”10″ blurb_length=”0″ show_thumb=”left”]
via Google News
The Latest on: Robot learning
- High school students set their eyes on international robotics competitionon November 28, 2023 at 11:36 am
They started with Robotics 1 - learning the building, coding and the basics of robotics. "Then as you go into a team, you find your individual role, which is where you want to compete, you want to ...
- Using large language models to code new tasks for robotson November 28, 2023 at 7:28 am
You've likely heard that "experience is the best teacher"—but what if learning in the real world is prohibitively expensive? This is the plight of roboticists training their machines on manipulation ...
- An approach that allows robots to learn in changing environments from human feedback and explorationon November 28, 2023 at 4:50 am
To best assist humans in real-world settings, robots should be able to continuously acquire useful new skills in dynamic and rapidly changing environments. Currently, however, most robots can only ...
- Worldwide Data Center Robotics Market Size Projected to Reach USD 63.93 Billion By 2032, With 22.2% CAGR: Polaris Market Researchon November 27, 2023 at 11:49 pm
As per the recent [115+ Pages] analysis by Polaris Market Research, the global data center robotics market size and share was valued at USD 8.64 billion in 2022 and is predicted to reach USD 63.93 ...
- New method uses crowdsourced feedback to help train robotson November 27, 2023 at 3:07 pm
A new technique enables an AI agent to be guided by data crowdsourced asynchronously from nonexpert human users as it learns to complete a task through reinforcement learning. The method trains the ...
- Games Where You Build Robotson November 27, 2023 at 2:34 pm
RELATED: Robots That Defined The Mecha Anime Genre Cogmind won’t appeal to a wide audience of gamers with its complex interface and steep learning curve, but with deep gameplay mechanics, this ...
- Cascade Learning Closes Reliability Gap for Robotic Vision AIon November 27, 2023 at 2:03 pm
Cascade learning has changed the automation game, attaining long-desired reliability with near 100% success rates in item picking.
- Researchers unveil robotic technology that could revolutionize how we use solar energy: ‘Machine learning has been very helpful’on November 27, 2023 at 2:00 pm
“In recent years, machine learning has been very helpful in better understanding the properties of materials. These studies require vast amounts of experimental data, and combining automated ...
- Innovative Approach Uses Crowdsourced Feedback to Accelerate Robot Learningon November 26, 2023 at 9:52 pm
A groundbreaking approach to teaching artificial intelligence (AI) agents, known as Human Guided Exploration (HuGE), has emerged as a transformative method in AI research. Developed collaboratively by ...
- Omani research explores impact of robot-aided learning in educationon November 26, 2023 at 9:21 am
A new research has explored the impact of using robots with different personalities in student engagement and learning in educational institutions in Oman.
via Bing News