Scribd Logo
Upload

Welcome to Scribd!

  • 19 views

    DWDM Unit4-2

    Uploaded by

    sri charan
    The document discusses classification using backpropagation in neural networks. It begins by defining backpropagation as a neural network learning algorithm developed by psychologists and neurobiologists. It then explains that a neural network consists of connected input/output units with associated weights. During learning, the network adjusts weights to predict the correct class label of inputs. The document also discusses strengths and weaknesses of using neural networks for classification and provides details on the structure and learning process of a multilayer feed-forward neural network using backpropagation.

    Copyright:

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

    DWDM Unit4-2

    Uploaded by

    sri charan
    19 views4 pages
    The document discusses classification using backpropagation in neural networks. It begins by defining backpropagation as a neural network learning algorithm developed by psychologists and neurobiologists. It then explains that a neural network consists of connected input/output units with associated weights. During learning, the network adjusts weights to predict the correct class label of inputs. The document also discusses strengths and weaknesses of using neural networks for classification and provides details on the structure and learning process of a multilayer feed-forward neural network using backpropagation.

    Original Description:

    s

    Original Title

    DWDM unit4-2

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    The document discusses classification using backpropagation in neural networks. It begins by defining backpropagation as a neural network learning algorithm developed by psychologists and neurobiologists. It then explains that a neural network consists of connected input/output units with associated weights. During learning, the network adjusts weights to predict the correct class label of inputs. The document also discusses strengths and weaknesses of using neural networks for classification and provides details on the structure and learning process of a multilayer feed-forward neural network using backpropagation.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    19 views4 pages

    DWDM Unit4-2

    Uploaded by

    sri charan
    The document discusses classification using backpropagation in neural networks. It begins by defining backpropagation as a neural network learning algorithm developed by psychologists and neurobiologists. It then explains that a neural network consists of connected input/output units with associated weights. During learning, the network adjusts weights to predict the correct class label of inputs. The document also discusses strengths and weaknesses of using neural networks for classification and provides details on the structure and learning process of a multilayer feed-forward neural network using backpropagation.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    of 4

    Classification by Backpropagation

    · Backpropagation: A neural network learning algorithm


    · Started by psychologists and neurobiologists to develop and test
    computational analogues of neurons
    · A neural network: A set of connected input/output units where each
    connection has a weight associated with it
    · During the learning phase, the network learns by adjusting the weights so
    as to be able to predict the correct class label of the input tuples
    · Also referred to as connectionist learning due to the connections between
    units

    Neural Network as a Classifier


    · Weakness
    o Long training time
    o Require a number of parameters typically best determined empirically, e.g., the
    network topology or ``structure."
    o Poor interpretability: Difficult to interpret the symbolic meaning behind the learned
    weights and of ``hidden units" in the network
    • Strength
    o High tolerance to noisy data
    o Ability to classify untrained patterns
    o Well-suited for continuous-valued inputs and outputs o Successful on a wide array
    of real-world data
    o Algorithms are inherently parallel
    o Techniques have recently been developed for the extraction of rules from trained
    neural networks

    A Multilayer Feed-Forward Neural Network


    o The inputs to the network correspond to the attributes measured for each training
    tuple
    o Inputs are fed simultaneously into the units making up the input layer
    o They are then weighted and fed simultaneously to a hidden layer
    o The number of hidden layers is arbitrary, although usually only one
    o The weighted outputs of the last hidden layer are input to units making up the output
    layer, which emits the network's prediction
    o The network is feed-forward in that none of the weights cycles back to an input unit
    or to an output unit of a previous layer
    o From a statistical point of view, networks perform nonlinear regression: Given
    enough hidden units and enough training samples, they can closely approximate
    any function
    Defining a network topology:
    • Specifying the number of units in the input layer, the number of hidden layers
    (if more than one), the number of units in each hidden layer, and the number
    of units in the output layer.
    • input values are normalized so as to fall between 0.0 and 1.0.
    • if an attribute A has three possible or known values, namely fa0, a1, a2g, then
    we may assign three input units to represent A. That is, we may have, say, I0,
    I1, I2 as input units.
    • Each unit is initialized to 0. If A D a0, then I0 is set to 1 and the rest are 0. If A
    D a1, then I1 is set to 1 and the rest are 0, and so on.
    Backpropagation Algorithm:
    Neural network learning for classification or numeric prediction, using the
    backpropagation algorithm.

    Input:
    • D, a data set consisting of the training tuples and their associated target values;
    • l, the learning rate;
    • network, a multilayer feed-forward network.
    Output: A trained neural network.
    Method

    Initialize the weights: The weights in the network are initialized to small random
    numbers (e.g., ranging from -1.0 to 1.0, or -0.5 to 0.5). Each unit has a bias associated
    with it, as explained later. The biases are similarly initialized to small random numbers.
    Each training tuple, X, is processed by the following steps.
    Propagate the inputs forward: First, the training tuple is fed to the network’s input
    layer. The inputs pass through the input units, unchanged. That is, for an input unit, j,
    its output, Oj , is equal to its input value, Ij . Next, the net input and output of each unit
    in the hidden and output layers are computed.

    Hidden or output layer unit j: The inputs to unit j are outputs from the previous layer.
    These are multiplied by their corresponding weights to form a weighted sum, which is
    added to the bias associated with unit j. A nonlinear activation function is applied to
    the net input. (For ease of explanation, the inputs to unit j are labelled y1, y2, ….. , yn.
    If unit j were in the first hidden layer, then these inputs would correspond to the input
    tuple (x1, x2, …. , xn).)

    You might also like