Scribd Logo
Upload

Welcome to Scribd!

  • 90 views

    Assignment Neural Networks

    Uploaded by

    Sagar Sharma
    The document discusses different types of learning rules for artificial neural networks: 1. Hebbian learning rule which increases weights between co-active neurons and decreases weights between inactive neurons. 2. Perceptron learning rule which is a supervised learning rule that adjusts weights to minimize error between actual and expected outputs. 3. Delta learning rule which modifies weights based on the product of input, error, and learning rate to reduce error over time. 4. Correlation learning rule which is similar to Hebbian but uses desired rather than actual responses in weight updates. 5. Outstar learning rule which sets weights to equal desired outputs for connected neurons. 6. Boltzmann learning rule

    Copyright:

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

    Assignment Neural Networks

    Uploaded by

    Sagar Sharma
    90 views7 pages
    The document discusses different types of learning rules for artificial neural networks: 1. Hebbian learning rule which increases weights between co-active neurons and decreases weights between inactive neurons. 2. Perceptron learning rule which is a supervised learning rule that adjusts weights to minimize error between actual and expected outputs. 3. Delta learning rule which modifies weights based on the product of input, error, and learning rate to reduce error over time. 4. Correlation learning rule which is similar to Hebbian but uses desired rather than actual responses in weight updates. 5. Outstar learning rule which sets weights to equal desired outputs for connected neurons. 6. Boltzmann learning rule

    Original Description:

    neural networks

    Original Title

    Assignment neural networks

    Copyright

    © © All Rights Reserved

    Available Formats

    DOCX, PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    The document discusses different types of learning rules for artificial neural networks: 1. Hebbian learning rule which increases weights between co-active neurons and decreases weights between inactive neurons. 2. Perceptron learning rule which is a supervised learning rule that adjusts weights to minimize error between actual and expected outputs. 3. Delta learning rule which modifies weights based on the product of input, error, and learning rate to reduce error over time. 4. Correlation learning rule which is similar to Hebbian but uses desired rather than actual responses in weight updates. 5. Outstar learning rule which sets weights to equal desired outputs for connected neurons. 6. Boltzmann learning rule

    Copyright:

    © All Rights Reserved
    Download as DOCX, PDF, TXT or read online from Scribd
    Download as docx, pdf, or txt
    90 views7 pages

    Assignment Neural Networks

    Uploaded by

    Sagar Sharma
    The document discusses different types of learning rules for artificial neural networks: 1. Hebbian learning rule which increases weights between co-active neurons and decreases weights between inactive neurons. 2. Perceptron learning rule which is a supervised learning rule that adjusts weights to minimize error between actual and expected outputs. 3. Delta learning rule which modifies weights based on the product of input, error, and learning rate to reduce error over time. 4. Correlation learning rule which is similar to Hebbian but uses desired rather than actual responses in weight updates. 5. Outstar learning rule which sets weights to equal desired outputs for connected neurons. 6. Boltzmann learning rule

    Copyright:

    © All Rights Reserved
    Download as DOCX, PDF, TXT or read online from Scribd
    Download as docx, pdf, or txt
    You are on page 1of 7

    ASSIGNMENT ON ARTIFICIAL NEURAL

    NETWORKS

    SUBMITTED TO: SUBMITTED BY:

    Prof. Jaimala Jha Nikunj Agrawal

    0901IT151025

    I.T. (final year)


    Que: Explain different types of learning rule?

    1.Hebbian learning rule:


    The Hebbian rule was the first learning rule. In
    1949 Donald Hebb developed it as learning algorithm of the unsupervised
    neural network. We can use it to identify how to improve the weights of nodes
    of a network.
    The Hebb learning rule assumes that – If two neighbor neurons activated and
    deactivated at the same time. Then the weight connecting these neurons should
    increase. For neurons operating in the opposite phase, the weight between them
    should decrease. If there is no signal correlation, the weight should not change.
    When inputs of both the nodes are either positive or negative, then a strong
    positive weight exists between the nodes. If the input of a node is positive and
    negative for other, a strong negative weight exists between the nodes.
    At the start, values of all weights are set to zero. This learning rule can be used0
    for both soft- and hard-activation functions. Since desired responses of neurons
    are not used in the learning procedure, this is the unsupervised learning rule.
    The absolute values of the weights are usually proportional to the learning time,
    which is undesired.
    2, Perceptron learning rule:
    As you know, each connection in a neural
    network has an associated weight, which changes in the course of learning.
    According to it, an example of supervised learning, the network starts its
    learning by assigning a random value to each weight.
    Calculate the output value on the basis of a set of records for which we can
    know the expected output value. This is the learning sample that indicates the
    entire definition. As a result, it is called a learning sample.
    The network then compares the calculated output value with the expected value.
    Next calculates an error function ∈, which can be the sum of squares of the
    errors occurring for each individual in the learning sample.
    Computed as follows:

    Perform the first summation on the individuals of the learning set, and perform
    the second summation on the output units. Eij and Oij are the expected and
    obtained values of the jth unit for the ith individual.
    The network then adjusts the weights of the different units, checking each time
    to see if the error function has increased or decreased. As in a conventional
    regression, this is a matter of solving a problem of least squares.
    Since assigning the weights of nodes according to users, it is an example of
    supervised learning
    3.Delta learning rule:
    Developed by Widrow and Hoff, the delta rule, is one of
    the most common learning rules. It depends on supervised learning.
    This rule states that the modification in sympatric weight of a node is equal to
    the multiplication of error and the input.
    In Mathematical form the delta rule is as follows:

    Mathematical Formula of Delta Learning Rule in Artificial Neural Network.

    For a given input vector, compare the output vector is the correct answer. If the
    difference is zero, no learning takes place; otherwise, adjusts its weights to
    reduce this difference. The change in weight from ui to uj is: dwij = r* ai * ej.
    where r is the learning rate, ai represents the activation of ui and ej is the
    difference between the expected output and the actual output of uj. If the set of
    input patterns form an independent set then learn arbitrary associations using
    the delta rule.
    It has seen that for networks with linear activation functions and with no hidden
    units. The error squared vs. the weight graph is a paraboloid in n-space. Since
    the proportionality constant is negative, the graph of such a function is concave
    upward and has the least value. The vertex of this paraboloid represents the
    point where it reduces the error. The weight vector corresponding to this point is
    then the ideal weight vector.
    We can use the delta learning rule with both single output unit and several
    output units.
    While applying the delta rule assume that the error can be directly measured.
    The aim of applying the delta rule is to reduce the difference between the actual
    and expected output that is the error.
    4. Correlation learning rule:
    The correlation learning rule based on a
    similar principle as the Hebbian learning rule. It assumes that weights between
    responding neurons should be more positive, and weights between neurons with
    opposite reaction should be more negative.
    Contrary to the Hebbian rule, the correlation rule is the supervised learning.
    Instead of an actual
    The response, oj, the desired response, dj, uses for the weight-change
    calculation.
    In Mathematical form the correlation learning rule is as follows:

    Mathematical Formula of Correlation Learning Rule in Artificial Neural


    Network.

    Where dj is the desired value of output signal. This training algorithm usually
    starts with the initialization of weights to zero.
    Since assigning the desired weight by users, the correlation learning rule is an
    example of supervised learning.
    5. Our star learning rule:
    We use the Out Star Learning Rule when we
    assume that nodes or neurons in a network arranged in a layer. Here the weights
    connected to a certain node should be equal to the desired outputs for the
    neurons connected through those weights. The out start rule produces the
    desired response t for the layer of n nodes.
    Apply this type of learning for all nodes in a particular layer. Update the
    weights for nodes are as in Kohonen neural networks.
    In Mathematical form, express the out star learning as follows:

    Mathematical Formula of Out Star Learning Rule in Artificial Neural Network.

    This is a supervised training procedure because desired outputs must be known.


    6.Boltzmann learning rule:
    The class of stochastic optimization problems
    can be viewed in terms of a network of nodes or units, each of which can be the
    si = +1 or si = −1 state. Every pair of nodes i and j is connected by the
    bidirectional weights wij ; if a weight between two nodes is zero, then no
    connection is drawn. The optimization problem is to find a configuration (i.e.
    assessment of all nodes) that minimizes the energy described by
    𝑁
    E=-1/2∑ wij xj x i≠j
    i
    𝑖,𝑗=1

    For pattern recognition the network structure presented in Fig.1 is used


    (Boltzmann network). It is important to distinguish between two types of visible
    units - d input units and c output units, which receive external binary feature
    and category information - as well as the remaining hidden units. During
    classification the input units are held fixed or clamped to the feature values of
    the input pattern; the remaining units are annealed to find the lowest-energy,
    most probable configuration. The category information is then read from the
    final values of the output units.

    You might also like