Scribd Logo
Upload

Welcome to Scribd!

  • 71 views

    ML Unit-5

    Uploaded by

    6682 Bhanu
    1. This unit discusses analytical learning and combining inductive and analytical learning approaches. 2. Analytical learning uses a domain theory and training examples to derive a hypothesis that is consistent with both, while inductive learning generalizes directly from examples. 3. Several methods are presented for combining inductive and analytical learning, such as using prior knowledge to initialize hypotheses or augment search operators during inductive learning.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd

    ML Unit-5

    Uploaded by

    6682 Bhanu
    71 views83 pages
    1. This unit discusses analytical learning and combining inductive and analytical learning approaches. 2. Analytical learning uses a domain theory and training examples to derive a hypothesis that is consistent with both, while inductive learning generalizes directly from examples. 3. Several methods are presented for combining inductive and analytical learning, such as using prior knowledge to initialize hypotheses or augment search operators during inductive learning.

    Original Title

    ML_UNIT-5

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    1. This unit discusses analytical learning and combining inductive and analytical learning approaches. 2. Analytical learning uses a domain theory and training examples to derive a hypothesis that is consistent with both, while inductive learning generalizes directly from examples. 3. Several methods are presented for combining inductive and analytical learning, such as using prior knowledge to initialize hypotheses or augment search operators during inductive learning.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    71 views83 pages

    ML Unit-5

    Uploaded by

    6682 Bhanu
    1. This unit discusses analytical learning and combining inductive and analytical learning approaches. 2. Analytical learning uses a domain theory and training examples to derive a hypothesis that is consistent with both, while inductive learning generalizes directly from examples. 3. Several methods are presented for combining inductive and analytical learning, such as using prior knowledge to initialize hypotheses or augment search operators during inductive learning.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    of 83

    UNIT 5

    ANALYTICAL LEARNING

    Analytical Learning-1: Introduction, learning with perfect domain theories:


    PROLOG-EBG, remarks on explanation-based learning, explanation-based
    learning of search control knowledge.
    Analytical Learning-2: Using prior knowledge to alter the search objective,
    using prior knowledge to augment search operators.
    Combining Inductive and Analytical Learning: Motivation, inductive-analytical
    approaches to learning, using prior knowledge to initialize the hypothesis.
    ANALYTICAL LEARNING
    Analytical Learning: A Definition

    Given a hypothesis space H a set of training examples D and a domain


    theory B consisting of background knowledge that can be used to
    explain observed training examples, the desired output of an analytical
    learner is a hypothesis h from H that is consistent with both the training
    examples D and the domain theory B.

    Explanation-Based-Learning works by generalizing not from the training


    examples themselves, but from their explanation.
    Learning With Perfect Domain Theories

    A perfect domain theory is correct and complete.


    A domain theory is correct if each of its assertions is a truthful
    statement about the world.
    A domain that is complete w.r.t target concept and X, if it covers
    every positive example in the instance space.
    Perfect domain theories are often unrealistic, but, learning in
    them is a first step before learning with imperfect theories.
    Prolog-EBG is an EBL learner. It uses sequential covering.
    Step1: Explain
    Step2: Analyze
    Summary of Prolog-EBG

    Prolog-EBG produces justified general hypotheses.


    1. The explanation of how the examples satisfy the target concept
    determines which examples attributes are relevant: those
    mentioned in the explanation.
    2. Regressing the target concept to determine its weakest
    preimage allows deriving more general constraints on the value
    of the relevant features.
    3. Each learned Horn Clause corresponds to a sufficient condition
    for satisfying the target concept.
    4. The generality of the learned Horn clauses depend on the
    formulation of the domain theory and on the sequence in
    which the training data are presented.
    5. Prolog-EBG implicitly assumes that the domain theory is correct
    and complete.

    20
    Different Perspectives on Explanation-
    Based-Learning (EBL)
    EBL as theory-guided generalization of examples: EBL
    generalizes rationally from examples.
    EBL as example-guided reformulation of theories: EBL can
    be viewed as a method for reformulating the domain
    theory into a more operational form.
    EBL as “just” restating what the learner already knows:
    EBL proceeds by reformulating knowledge and this can
    sometimes be seen as an important kind of learning (the
    difference between knowing how to play chess and
    knowing how to play chess well, for example!)

    21
    EBL of Search Control Knowledge
    Given EBL’s restriction to domains with a correct and complete
    domain theory, an important class of application is in speeding
    up complex search problems by learning how to control search.
    Two well-known systems employ EBL in such a way: PRODIGY
    and SOAR.
    In PRODIGY, the questions that need to be answered during the
    search problem are: “Which subgoals should be solved next?”
    and “Which operator should be considered for solving this
    subgoal?”. PRODIGY learns concepts such as “the set of states in
    which subgoal A should be solved before subgoal B”.

    22
    EBL of Search Control Knowledge
    SOAR learns by explaining situations in which its
    current strategy leads to inefficiencies. More
    generally, SOAR uses a variant of EBL called chunking
    to extract the general conditions under which the
    same explanation applies.
    SOAR has been applied in a great number of problem
    domain and has also been proposed as a
    psychologically plausible model of human learning
    processes.

    23
    Problems associated with applying EBL to
    Learning Search Control
    In many cases, the number of control rules that must be
    learned is very large. As the system learns more and more
    control rules to improve its search, it must pay a larger
    and larger cost at each step to match this set of rules
    against the current search state.
    In many cases, it is intractable to construct the
    explanations for the desired target concept.

    24
    Standard Approach to EBL

    29
    The EBL Process

    31
    An Example
    Domain theory:
    Fixes(u,u)➔ Robust(u) // An individual that can fix itself is robust
    Sees(x,y)  Habile(x) ➔Fixes(x,y) // A habil individual that can see another entity can
    // fix that entity
    Robot(w) ➔Sees(w,w) // All robots can see themselves
    R2D2(x) ➔ Habile(x) // R2D2-class in individuals are habil
    ………

    Facts:
    Robot(Num5)
    R2D2(Num5)
    Age(Num5,5)
    ………

    Goal:
    Robust(Num5)

    32
    An Example (continued…)

    Generalization

    Explain

    Robot(r)  R2D2(r) ➔Robust(r)


    33
    History ??
    EBL may be viewed as a convergence of several distinct lines of research
    within machine learning.
    EBL has developed out of efforts to address each of the following
    problems:
    ◦ Justified generalization.
    ◦ Chunking.
    ◦ Operationalization.
    ◦ Justified analogy.

    34
    Conclusions

    • Explanation Based Learning (EBL):


    • Needs only one example.
    • Requires complete knowledge about the concept.
    • Shows the importance of prior knowledge in learning.

    35
    Chapter 2
    Analytical Learning-2: Using prior knowledge to alter the search objective,
    using prior knowledge to augment search operators.
    Using prior knowledge to alter the search objective
    Using prior knowledge to alter the search objective
    The EBNN Algorithm
    Domain theory
    Each rectangular Hock represents a
    distinct neural network in the
    domine theory
    •There is one network for each Horn clause in the domain theory.
    •EBNN uses the top network to calculate the partial derivative of the
    prediction with respect to each feature of the instance. (i.e., how much
    does the output change as I tweak BottomIsFlat?).
    •These derivatives are given to the bottom network which is trained with
    a variation of TangentProp.
    The TANGENTPROP
    Summery TANGENTPROP
    Algorithm
    Remarks
    Remarks
    Using prior knowledge to augment search operators
    Using prior knowledge to augment search operators
    Dashed edges in the search
    tree denotes an additional
    l candidate specialization that
    is considered by FOCL and
    based on the domain theory

    Solid edges in the search tree show


    the general to specific search
    steps considered in a typical
    Search by FOIL
    Chapter 3

    Combining Inductive and Analytical Learning:


    Motivation, inductive-analytical approaches
    to learning, using prior knowledge to initialize
    the hypothesis.
    Combining Inductive and Analytical Learning
    Using prior knowledge to initialize
    the hypothesis
    Example: The Cup Learning Task

    You might also like