& Expert Systems-General

download & Expert Systems-General

of 27

Transcript of & Expert Systems-General

  • 8/6/2019 & Expert Systems-General

    1/27

    Expert Systems

    KR Chowdhary, Associate Professor,

    Department of Computer Science & Engineering,MBM Engineering College, JNV University, Jodhpur,

    [email protected]

  • 8/6/2019 & Expert Systems-General

    2/27

    Defining Expert Systems

    Definitions:

    Where human expertise is needed to solve problems,expert systems are likely candidates to solve thoseproblems.

    What is an expert system (ES)?

    A set of programs that manipulate encodedknowledge to solve problems in a specialized domainthat normally require human expertise.

    Encoded knowledge is used in inferencing orreasoning process.

  • 8/6/2019 & Expert Systems-General

    3/27

    Uses knowledge rather than data for controlthe solution.

    Knowledge is maintained separate from

    control program ES are capable of explaining howand whya

    particular solution arrived.

    Uses symbolic representation of knowledge

    and performs symbolic computation whichclosely matches human beings.

    Uses meta-knowledge.

    Characteristic features of ES:

  • 8/6/2019 & Expert Systems-General

    4/27

    Applications of Expert Systems

    Medical Diagnoses

    Diagnosis of complex electronic andelectromechanical systems

    Diagnosis of software development projects Weather forecasting

    Forecasting crop damages

    Identification of chemical compound

    structures Location faults in computer and

    communication systems

  • 8/6/2019 & Expert Systems-General

    5/27

    Applications

    Scheduling of Customer orders, jobs in OS, inproductions.

    Evaluation of applications for loan, eligibility

    criteria, etc. VLSI Design

    Military applications, like those in battle fields

    Law area, like-civil laws, disputes, etc.

    Teaching AI techniques

  • 8/6/2019 & Expert Systems-General

    6/27

    Why to use ES?

    Commercial viability: whereas there may be only a few expertswhose time is expensive and rare, you can have many expertsystems

    expert systems can be used anywhere, anytime

    expert systems can have more knowledge than experts expert systems can explain their line of reasoning

    Weaknesses:

    expert systems are as sound as their KB; errors in rules meanerrors in diagnoses

    automatic error correction, learning is difficult (although machinelearning research may change this)

    little common sense reasoning: idiot servants

  • 8/6/2019 & Expert Systems-General

    7/27

    Rule-based Expert Systems

    These are most common type of ES

    Uses the knowledge encoded in the form ofproduction rules (ifthen .. rules), i.e.

    1. If cond1 and cond2 and cond3

    Then take action-12. If temperature > 200 deg and water level low

    Then open the safety valve

    Each rule represents a small chunk of knowledgerelating the given domain

    A number of rules may give a chain of inferencesstarting from some known facts to usefulconclusions.

  • 8/6/2019 & Expert Systems-General

    8/27

    Input

    Output

    UserExplanatio

    n Module

    I/O

    Interface

    Editor

    InferenceEngine CaseHistory

    File

    KB WorkingMemory

    Learning

    Module

    Expert System

  • 8/6/2019 & Expert Systems-General

    9/27

    Expert System..

    User interface:

    Question answer type

    Menu-driven

    Natural language

    Graphic interface

  • 8/6/2019 & Expert Systems-General

    10/27

    KB: Contains facts and rules about some specialized domain.

    Building KB using editor.

    Inference Process: Inference Engine accepts user input

    queries in response to questions through I/O interface.Inference process is carried out by three stages: match, select,execute.

    What is match?

    contents of working memory are compared with KB. Whenmatch is found, the corresponding rules are placed in theconflict set (i.e. select). Further it needs instantiations toconfirm match. This follows execution.

    Expert System..

  • 8/6/2019 & Expert Systems-General

    11/27

    Inferencing

    KB Working

    Memory

    1. Match

    Conflict Set

    2. Select

    3. Execute

    Inference Cycle

  • 8/6/2019 & Expert Systems-General

    12/27

    Prolog uses backward chaining (goal driven strategy),matching of sub goals for the goal to be achieved.

    Rules may be tested exhaustively or selectivelydepending on the control strategy.

    The chaining continues as long as matches can befound between clauses in the working memory andthe rules in the KB.

    The search can be limited to few hundred rules.

    Uncertainty measures can also be used

    Prolog rules:

  • 8/6/2019 & Expert Systems-General

    13/27

    Explaining how&why?

    How did you know that? (for inference result)

    Why do you need to know that? (when additionalinformation is asked)

    I/O Interface: Permits the user to communicatewith the system in a more natural may by permittingthe the use of simple selection menus or use of a

    restricted natural language.

    Explanation

  • 8/6/2019 & Expert Systems-General

    14/27

    Explanation..

    When you are asking why a particular action wasperformed at a node in the tree... how questions: recite the children

    why questions: recite the parent

    thus backward chaining expert systems naturallysupport explanation can be done during inference: when user asked for data,

    s/he can as why and a reason is given

    after expert advice given, user can ask how, why, andeven why not (ie. why did some rule fail)

    a great tool for KB debugging! forward chaining: explanation not as structured;

  • 8/6/2019 & Expert Systems-General

    15/27

    Knowledge Acquisition andvalidation

    This is also called knowledge engineeringprocess

    Needs acquiring of knowledge and thenencoding it

    Knowledge is derived from experts, journals,texts, reports, interviews, etc.

    Job is performed by knowledge engineer.

    Consolidating of the knowledge may needcollective efforts of many persons.

  • 8/6/2019 & Expert Systems-General

    16/27

    Knowledge acquisition process

    Domain

    Expert KBSystem

    Editor

    Knowledge

    Engineer

  • 8/6/2019 & Expert Systems-General

    17/27

    1. Medical expert systemsMedical expert systems are an active area.

    Humanitarian uses: remote areas can have world-classexpertise,

    medical science is complex; expert systems are intelligent

    advisors and assistants MYCIN

    diagnose bacterial infections

    uses certainty factors: ranked diagnoses are generated

    EMYCIN: empty MYCIN - the shell of MYCIN for use in otherapplications

    CADUCEUS: expert system with entire internal medicine KB

    its been active since 1970s

    Examples expert systems

  • 8/6/2019 & Expert Systems-General

    18/27

    2. XCON configures VAX systems from user requirements

    DEC uses it; has increased throughput of systemdesign

    10,000 rules said to have replaced X system designers with 4X

    expert system maintainers!

    3. DELTA/CATS diesel electric locomotive trouble shooter

    problem: system maintenance

    Examples expert systems

  • 8/6/2019 & Expert Systems-General

    19/27

    4. Jonathans Wave commodities trading

    incorporates several experts approaches

    runs in Prolog and C

    lots of AI groups on Wall Street!

    5. DENDRAL(1960): For determining the structure of chemicalcompounds given its specification.

    6. PROSPECTOR:Assists the geologists in discovering theminerals deposits.

    Examples expert systems

  • 8/6/2019 & Expert Systems-General

    20/27

    7. Codecheck expert system to evaluate C source code

    complexity, formatting, standards and portability adherence

    identifies overly complex code (prime source of programproblems!)

    8. CHORAL expert system for harmonizing chorales in the style of J.S.

    Bach

    similar system: harmonic analysis of tonal music

    rules obtained from: studying composers music,

    musicologists some systems used for composition (with interesting results)

    Examples expert systems

  • 8/6/2019 & Expert Systems-General

    21/27

    Expert systems are now ubiquitous (I.e.,present every where)

    still lots of active research:

    probabilistic knowledge and deduction

    large system maintenance

    knowledge acquisition popular domains

    industrial, financial, medical

    legal: interpret laws by the book

    education: intelligent tutoring

    Some domains remain difficult to implement those requiring artistic creativity and skill

    those requiring common sense

    The state of the art

  • 8/6/2019 & Expert Systems-General

    22/27

    The need for a solution must justify the costsinvolved in development

    Human expertise is not available in all situationswhere it is needed

    The problem may be solved using symbolic reasoningtechniques

    The problem is well structured and does not require(much) common sense knowledge

    The problem cannot be easily solved using more

    traditional computing methods Cooperative and articulate experts exist

    The problem is of proper size and scope

    Steps in expert system building:Choosing Problem:

  • 8/6/2019 & Expert Systems-General

    23/27

    expert system building is a software engineeringtask, but with a twist: knowledge base KB will be continually refined, corrected, updated

    expert system design & implementation steps

    1. initial proposal - identification of problem, expert(s), benefits2. create a prototype

    3. knowledge engineering: interview expert for many weeks(months)

    4. implement experts expertise in KB

    5. test expert system; go to 3 (let expert see results)

    6. put in production ; refine errors when found

    Steps in expert system building

  • 8/6/2019 & Expert Systems-General

    24/27

    Knowledge engineering: the extraction of knowledge from anexpert, and encoding it into machine-inferrable form

    K.E. is the most difficult part of expert system implementation

    the knowledge engineer must extract detailed info from anexpert; but s/he is not expected to understand it

    the expert relies on years of experience and intuition: askingthem to deconstruct knowledge is difficult and frustrating

    can also be political factors

    many strategies for knowledge engineering

    multiple KEs

    multiple experts

    watch expert in the field

    continual expert feedback on expert system performance

    Knowledge engineering

  • 8/6/2019 & Expert Systems-General

    25/27

    Other types of expert system

    Called Non-production systems

    These are:

    Semantic Network based

    Frame based

    Decision tree based

    Neural net based

  • 8/6/2019 & Expert Systems-General

    26/27

    Problems of using expertsystems

    Choice of domain

    Acceptability

    Uncertainty

    Updating Limitation (ES do not know itself)

    Testing

    Behavior

    Knowledge acquisition

  • 8/6/2019 & Expert Systems-General

    27/27

    Advantages of using expertSystems

    Availability

    Consistency

    Comprehensiveness (detailedknowledge)