Unlock instant, AI-driven research and patent intelligence for your innovation.

Adaptive multi-agent cooperative computation and inference

A computer and processor technology applied in the field of adaptive multi-agent collaborative computing and statistical inference

Active Publication Date: 2019-12-31
IBM CORP
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Traditional SI suffers from a fundamental limitation: cluster behavior is strictly restricted to in-plant programming—a pre-defined set of simple rules governing each individual

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Adaptive multi-agent cooperative computation and inference
  • Adaptive multi-agent cooperative computation and inference
  • Adaptive multi-agent cooperative computation and inference

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0018] Although SI devices are flexible, the rules governing the behavior of each device are predefined and relatively simple. The illustrative embodiments recognize that these types of rules cannot be quickly adjusted to adapt to environmental changes encountered in the outside world, and are also not sufficient for unexpected situations that require real-time or near-real-time adaptation—such as sudden (unexpected) changes in the surrounding environment. , glitches, or the need to learn new tasks in a hurry. Machine-learning classifiers can learn from experience, but they also don't respond well to sudden changes in the patterns of field data that differ significantly from the data sets used during in-plant training.

[0019] Two examples illustrate these situations, one involving autonomous vehicles and the other in the field of cybersecurity.

[0020] Autonomous vehicles must recognize objects and react accordingly. For example, a self-driving car or truck must recognize...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

In a first device in response to an event input, using a processor and a memory, a local classification and a local classification confidence score corresponding to the event input are computed. At the first device in response to a broadcast request, a remote classification and a remote classification confidence score corresponding to the event input are received, the remote classification and theremote classification confidence score being computed at a second device. At the first device, a consensus classification including the most frequent classification from a set of all received remoteclassifications and the local classification is formed, provided the number of classifications including the most frequent classification exceeds a threshold. In response to a consensus classificationconfidence score corresponding to the consensus classification exceeding a confidence threshold, a local classification model is updated. Based on the local classification and the consensus classification, the event input is assigned to a classification.

Description

[0001] government rights [0002] This invention was made with Government support under HR0011-13-C-0022 awarded by the Microsystems Technologies Office (MTO) of the Defense Advanced Research Projects Agency. The government has certain rights in this invention. technical field [0003] The present invention generally relates to methods, systems and computer program products for solving intelligent problems. More specifically, the present invention relates to methods, systems and computer program products for adaptive multi-agent collaborative computation and statistical inference employing field learning. Background technique [0004] Swarm intelligence (SI)—the collective behavior of decentralized self-organizing systems, natural or artificial—is relatively well known. A typical SI system includes a population of simple units (or agents)—devices or instances of software-hardware devices—that interact locally with each other and with their environment. (Agents are softwar...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): H04L12/801H04L12/851H04L29/06G06K9/62
CPCH04L47/2441H04L47/29H04L63/1458G06F18/241G05D1/0289H04L67/12H04W12/12H04L63/0227H04W4/40G06N5/043G06N3/08G06N3/006H04W12/66H04W12/67H04W12/088G06N3/045G05D1/0088G06N20/00G06N7/01
Inventor A·维加P·博塞A·布于克托苏诺格卢
Owner IBM CORP