Scribd Logo
Upload

Welcome to Scribd!

  • Probalistics Methods For Uncertain Reasoning

    Uploaded by

    Kumar Gaurav
    10 views1 page
    about mathe

    Original Title

    Probalistics methods for uncertain reasoning.txt

    Copyright

    © Attribution Non-Commercial (BY-NC)

    Available Formats

    TXT, PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    Report this Document
    about mathe

    Copyright:

    Attribution Non-Commercial (BY-NC)
    Download as TXT, PDF, TXT or read online from Scribd
    Flag for inappropriate content
    10 views1 page

    Probalistics Methods For Uncertain Reasoning

    Uploaded by

    Kumar Gaurav
    about mathe

    Copyright:

    Attribution Non-Commercial (BY-NC)
    Download as TXT, PDF, TXT or read online from Scribd
    Flag for inappropriate content
    of 1

    <html> <head> <title>Probabilistic methods for uncertain reasoning</title> </head> <body color= black ><font size="+3" face="arial black"

    color="blue"><b><u><center><i mj src="a.html">Probabilistic methods for uncertain reasoning</body></font></b>< /u></center><p><basefont size="+2"color="orange"> <font size=+2>Many problems in AI (in reasoning, planning, learning, perception and robotics) require the agent to operate with incomplete or uncertain informat ion. AI researchers have devised a number of powerful tools to solve these probl ems using methods from probability theory andeconomics.[117] <p>Bayesian networks[118] are a very general tool that can be used for a large n umber of problems: reasoning (using the Bayesian inferencealgorithm),[119] learn ing (using the expectation-maximization algorithm),[120] planning (using decisio n networks)[121] and perception (usingdynamic Bayesian networks).[122] Probabili stic algorithms can also be used for filtering, prediction, smoothing and findin g explanations for streams of data, helping perception systems to analyze proces ses that occur over time (e.g., hidden Markov models or Kalman filters).[122] <p>A key concept from the science of economics is "utility": a measure of how va luable something is to an intelligent agent. Precise mathematical tools have bee n developed that analyze how an agent can make choices and plan, using decision theory, decision analysis,[123] information value theory.[58] These tools includ e models such as Markov decision processes,[124] dynamic decision networks,[122] game theory and mechanism design.[125] </html>

    You might also like