Everand Logo

Welcome to Everand!

  • Explore 1.5M+ audiobooks & ebooks free for days

    Only $12.99 CAD/month after trial. Cancel anytime.

    Distributed Artificial Intelligence: Fundamentals and Applications
    Distributed Artificial Intelligence: Fundamentals and Applications
    Distributed Artificial Intelligence: Fundamentals and Applications
    Ebook101 pages1 hourArtificial Intelligence

    Distributed Artificial Intelligence: Fundamentals and Applications

    By Fouad Sabry

    ()

    Read preview

    About this ebook

    What Is Distributed Artificial Intelligence


    Research in the area of artificial intelligence known as Distributed Artificial Intelligence (DAI), which is often referred to as Decentralized Artificial Intelligence, is a subfield that focuses on the creation of distributed solutions for various types of challenges. The field of multi-agent systems is closely related to and was actually preceded by the discipline of DAI.


    How You Will Benefit


    (I) Insights, and validations about the following topics:


    Chapter 1: Distributed Artificial Intelligence


    Chapter 2: Artificial Intelligence


    Chapter 3: List of Artificial Intelligence Projects


    Chapter 4: Software Agent


    Chapter 5: Cooperative Distributed Problem Solving


    Chapter 6: Multi-Agent System


    Chapter 7: Swarm Robotics


    Chapter 8: Blackboard System


    Chapter 9: Belief–Desire–Intention Software Model


    Chapter 10: Multi-Agent Planning


    (II) Answering the public top questions about distributed artificial intelligence.


    (III) Real world examples for the usage of distributed artificial intelligence in many fields.


    Who This Book Is For


    Professionals, undergraduate and graduate students, enthusiasts, hobbyists, and those who want to go beyond basic knowledge or information for any kind of distributed artificial intelligence.

    LanguageEnglish
    PublisherOne Billion Knowledgeable
    Release dateJun 24, 2023
    Distributed Artificial Intelligence: Fundamentals and Applications

    Other titles in Distributed Artificial Intelligence Series (30)

    View More
    View More

    Read more from Fouad Sabry

    Related to Distributed Artificial Intelligence

    Titles in the series (100)

    View More
    View More

    Related ebooks

    Intelligence (AI) & Semantics For You

    View More
    View More

    Related categories

    Reviews for Distributed Artificial Intelligence

    0 ratings

    0 ratings0 reviews

    What did you think?

    Tap to rate

    Review must be at least 10 words

      Book preview

      Distributed Artificial Intelligence - Fouad Sabry

      Chapter 1: Distributed artificial intelligence

      Research in the area of artificial intelligence known as Distributed Artificial Intelligence (DAI), which is often referred to as Decentralized Artificial Intelligence, is a branch that focuses on the creation of distributed solutions for many types of challenges. The area of multi-agent systems is closely connected to and developed out of DAI, which was its forerunner.

      The two most prominent DAI techniques are known as multi-agent systems and distributed problem solving. There are many different programs and tools available.

      The term distributed artificial intelligence (DAI) refers to a strategy for resolving complicated issues including learning, planning, and decision-making. It is so parallel that it is humiliating, and as a result, it can take advantage of large-scale processing and the geographical distribution of computer resources. Because of these qualities, it is able to tackle issues that need the processing of very extensive data sets. DAI systems are made up of autonomous learning processing nodes, also known as agents, which are spread out over a network, often on a very large scale. Nodes in a DAI system are able to function on their own, and communication between the nodes allows for the integration of incomplete answers in a manner that is often asynchronous. DAI systems are characterized as resilient and elastic, and they are required to be loosely connected because of their size. In addition, given to the complexity of the challenge and the difficulties involved in redeployment, DAI systems are designed to be able to adapt to changes in the problem description or the underlying data sets.

      In contrast to monolithic or centralized Artificial Intelligence systems, which feature processing nodes that are closely connected and located in close proximity to one another, Distributed Artificial Intelligence (DAI) systems do not need all of the important data to be gathered in a single area. As a result, deep learning artificial intelligence systems often run on subsamples or hashed representations of extremely large datasets. In addition, the dataset that serves as the source may undergo modifications or enhancements while a DAI system is being put into operation.

      Artificial intelligence was split into many subfields in 1975, one of which was distributed artificial intelligence, which dealt with the interactions of intelligent agents. The major focus of attention in multi-agent systems is on the manner in which agents coordinate their respective knowledge and activity. When addressing problems in a distributed manner, the primary attention should be on how the problems are decomposed and how the answers are synthesised.

      The goal of Distributed Artificial Intelligence is to solve the reasoning, planning, learning, and perception problems that are associated with artificial intelligence, particularly those that call for large amounts of data. This is accomplished by delegating the processing of the problem to a network of independent processing nodes (agents). DAI needs to have in order to accomplish the goal:

      A distributed system with robust and elastic computation on unreliable and failing resources that are loosely coupled

      Coordination of the activities of the nodes as well as their communication

      Using smaller samples from larger data sets in conjunction with online machine learning

      There are a lot of different factors to consider while deciding whether or not to disperse intelligence or deal with multi-agent systems. The following are examples of issues that are often encountered in DAI research::

      The primary focus of parallel problem solving is on the ways in which traditional ideas from artificial intelligence may be adapted such that multiprocessor systems and computer clusters can be utilized to increase the rate at which calculations are performed.

      Distributed problem solving (DPS): in order to serve as an abstraction for the development of DPS systems, the notion of agent, which refers to independent entities that are able to interact with one another, was invented. Please see the list below for additional explanation.

      Multi-Agent Based Simulation, commonly known as MABS, is a subfield of DAI that lays the groundwork for simulations that need to investigate phenomena not just at the macro level but also at the micro level, as is the case in many different types of social simulation situations.

      There are now two distinct forms of DAI:

      Agents in multi-agent systems reason about the processes of coordinating their knowledge and actions as well as coordinate their knowledge and activities. Agents are entities, either real or virtual, that are capable of acting, perceiving their surroundings, and communicating with other agents. The agent is self-sufficient and has the abilities necessary to accomplish objectives. Because of the acts that they do, the agents alter the condition of their surroundings. There are a variety of methods that may be used to coordinate activities.

      The task of addressing a problem is dispersed over several nodes, and the information gained from those nodes is shared. The division of the tasks and the synthesis of the relevant information and solutions are the primary considerations.

      DAI is capable of using a bottom-up approach to AI, which is analogous to the architecture of subsumption, in addition to the more conventional top-down approach to AI. In addition to this, DAI also has the potential to serve as a vehicle for emergence.

      The difficulties associated with distributed AI are as follows::

      How to carry out communication and interaction amongst agents, as well as which communication language or protocols need to be used.

      How to make sure that all of the agents are coherent.

      How to synthesize the outcomes of the 'intelligent agents' group by way of formulation, description, decomposition, and allocation.

      The following are some of the areas where DAI has been applied::

      The use of electronic commerce, for example, in the formulation of trading strategies The DAI system is

      Enjoying the preview?
      Page 1 of 1