Scribd Logo
Upload

Welcome to Scribd!

  • 12 views

    Self Organizing Maps

    Uploaded by

    Vaanya Saxena
    The document discusses Self Organizing Maps (SOM), an unsupervised neural network technique. SOM learns the topological ordering of input data and maps it to lower dimensional space. The document describes the SOM algorithm, architecture, training process involving competition, cooperation and synaptic adaptation, and properties like approximation of input space and topological ordering.

    Copyright:

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

    Self Organizing Maps

    Uploaded by

    Vaanya Saxena
    12 views22 pages
    The document discusses Self Organizing Maps (SOM), an unsupervised neural network technique. SOM learns the topological ordering of input data and maps it to lower dimensional space. The document describes the SOM algorithm, architecture, training process involving competition, cooperation and synaptic adaptation, and properties like approximation of input space and topological ordering.

    Copyright

    © © All Rights Reserved

    Available Formats

    PPTX, PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    The document discusses Self Organizing Maps (SOM), an unsupervised neural network technique. SOM learns the topological ordering of input data and maps it to lower dimensional space. The document describes the SOM algorithm, architecture, training process involving competition, cooperation and synaptic adaptation, and properties like approximation of input space and topological ordering.

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd
    Download as pptx, pdf, or txt
    12 views22 pages

    Self Organizing Maps

    Uploaded by

    Vaanya Saxena
    The document discusses Self Organizing Maps (SOM), an unsupervised neural network technique. SOM learns the topological ordering of input data and maps it to lower dimensional space. The document describes the SOM algorithm, architecture, training process involving competition, cooperation and synaptic adaptation, and properties like approximation of input space and topological ordering.

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd
    Download as pptx, pdf, or txt
    of 22

    Self Organizing

    Maps(SOM)
    SOM- Introduction
    • Networks are based on competitive learning
    • Neurons are placed at nodes of lattice
    • Nonlinear
    • Characterized by the formation of topographic maps
    • Motivation by cerebral cortex (Kass et.al 1983)
    • It follows an unsupervised learning approach
    • SOM has two layers, one is the Input layer and the other one is the Output
    layer.
    • The architecture of the Self Organizing Map with two clusters and n input
    features of any sample is given below:
    • How do SOM works?
    • Input data of size (m, n)
    • First, it initializes the weights of size (n, C) where C is the number of clusters.
    • Then iterating over the input data, for each training example, it updates the
    winning vector.
    • Weight updating rule is given by :
    wij = wij(old) + α(t) * (xik - wij(old))

    • where α is a learning rate at time t,


    • j denotes the winning vector,
    • i denotes the ith feature of training example
    • k denotes the kth training example from the input data.
    After training the SOM network, trained weights are used for clustering new
    examples. A new example falls in the cluster of winning vectors.
    SOM Algorithm

    Kohonen Self-Organizing Feature Map Architecture


    KSOFM
    SOM Algorithm….
    SOM Algorithm
    Training:
    • Step 1: Initialize the weights wij random value may be assumed. Initialize the
    learning rate α.
    • Step 2: Calculate squared Euclidean distance.
    • D(j) = Σ (wij – xi)^2 where i=1 to n and j=1 to m
    • Step 3: Find index J, when D(j) is minimum that will be considered as winning
    index.
    • Step 4: For each j within a specific neighborhood of j and for all i, calculate the
    new weight.
    • wij(new)=wij(old) + α[xi – wij(old)]
    • Step 5: Update the learning rule by using :
    • α(t+1) = 0.5 * α(t)
    • Step 6: Test the Stopping Condition.
    Kohonen Algorithm
    Self Organizing Maps
    • Self-organizing maps are based on competitive learning; the output neurons
    of the network compete among themselves to be activated or fired, with the
    result that only one output neuron, or one neuron per group, is on at any one
    time.
    • An output neuron that wins the competition is called a winner-takes all
    neuron, or simply a winning neuron.
    • The self-organizing map is inherently nonlinear.
    • As a neural model, the self-organizing map provides a bridge between two
    levels of adaptation:
    • adaptation rules formulated at the microscopic level of a single neuron;
    • formation of experientially better and physically accessible patterns of
    feature selectivity at the microscopic level of neural layers.
    Types of Self Organizing Maps
    Types of Self Organizing Maps
    SOM Process
    Three essential processes involved in the formation of the self-organizing map.

    1. Competition. For each input pattern, the neurons in the network compute their respective values
    of a discriminant function. This discriminant function provides the basis for competition among the
    neurons. The particular neuron with the largest value of discriminant function is declared winner of
    the competition.

    2. Cooperation. The winning neuron determines the spatial location of a topological neighborhood
    of excited neurons, thereby providing the basis for cooperation among such neighbouring neurons.

    3. Synaptic Adaptation. This last mechanism enables the excited neurons to increase their individual
    values of the discriminant function in relation to the input pattern through suitable adjustments
    applied to their synaptic weights.
    SOM Process
    two phases of the adaptive process:
    1. Self-organizing or ordering phase: It is during this first phase of the
    adaptive process that the topological ordering of the weight vectors takes
    place.
    2. Convergence phase: This second phase of the adaptive process is needed
    to fine tune the feature map and therefore provide an accurate statistical
    quantification of the input space.
    Essence of Kohonen’s Algorithm
    • The essential ingredients and parameters of the algorithm are as
    follows:
    • a continuous input space of activation patterns that are generated in
    accordance with a certain probability distribution;
    • a topology of the network in the form of a lattice of neurons, which
    defines a discrete output space;
    • a time-varying neighborhood function hj,i(x) (n) that is defined around a
    winning neuron i(x);
    • a learning-rate parameter (n) that starts at an initial value 0 and then
    decreases gradually with time n, but never goes to zero.
    Learning Algorithm
    • The algorithm is summarized as follows:
    Learning Algorithm
    PROPERTIES OF THE FEATURE MAP
    • Once the SOM algorithm has converged, the feature map computed by the
    algorithm displays important statistical characteristics of the input space.

    • Property 1. Approximation of the Input Space


    • Property 2. Topological Ordering

    You might also like