Scribd Logo
Upload

Welcome to Scribd!

  • 183 views

    Artificial Neural Networks - MiniProject

    Uploaded by

    amithbalu
    The document provides an overview of artificial neural networks, including biological neuron models, artificial neuron models, network architecture, learning methods like backpropagation, and applications. It describes how artificial neural networks are inspired by biological brain structure and function, using basic neural network components like nodes/weights to perform tasks through a learning process like backpropagation that reduces error.

    Copyright:

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

    Artificial Neural Networks - MiniProject

    Uploaded by

    amithbalu
    183 views16 pages
    The document provides an overview of artificial neural networks, including biological neuron models, artificial neuron models, network architecture, learning methods like backpropagation, and applications. It describes how artificial neural networks are inspired by biological brain structure and function, using basic neural network components like nodes/weights to perform tasks through a learning process like backpropagation that reduces error.

    Original Description:

    small demo on artificial neural networks

    Original Title

    Artificial Neural Networks_MiniProject

    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 provides an overview of artificial neural networks, including biological neuron models, artificial neuron models, network architecture, learning methods like backpropagation, and applications. It describes how artificial neural networks are inspired by biological brain structure and function, using basic neural network components like nodes/weights to perform tasks through a learning process like backpropagation that reduces error.

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd
    Download as pptx, pdf, or txt
    183 views16 pages

    Artificial Neural Networks - MiniProject

    Uploaded by

    amithbalu
    The document provides an overview of artificial neural networks, including biological neuron models, artificial neuron models, network architecture, learning methods like backpropagation, and applications. It describes how artificial neural networks are inspired by biological brain structure and function, using basic neural network components like nodes/weights to perform tasks through a learning process like backpropagation that reduces error.

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd
    Download as pptx, pdf, or txt
    of 16
    At a glance
    Powered by AI
    The key takeaways are the introduction to artificial neural networks, their biological inspiration, architecture and learning mechanisms.

    The main components of an artificial neuron are inputs, weights, summation function and activation function.

    An artificial neural network learns by modifying the weights of connections between nodes through a process called training, where the network learns from examples.

    MINI PROJECT ON

    ARTIFICIAL NEURAL NETWORKS


    CONTENTS
    INTRODUCTION
    BIOLOGICAL NEURON MODEL
    ARTIFICIAL NEURON MODEL
    ARTIFICIAL NEURAL NETWORK
    NEURAL NETWORK ARCHITECTURE
    LEARNING
    BACKPROPAGATION ALGORITHM
    APPLICATIONS
    ADVANTAGES
    CONCLUSION
    INTRODUCTION
    An artificial neuron is a mathematical function conceived as a model
    of biological neurons . Artificial Neurons are the constitutive units in
    an Artificial Neural Network.
    Neural is an adjective for neuron, and network denotes a graph
    like structure.
    Artificial Neural Networks are also referred to as neural nets ,
    artificial neural systems, parallel distributed processing systems,
    connectionist systems.
    BIOLOGICAL NEURON MODEL

    Four parts of a typical nerve cell : -


    DENDRITES: Accepts the inputs
    SOMA : Process the inputs
    AXON : Turns the processed inputs into
    outputs.
    SYNAPSES : The electrochemical
    contact between the
    neurons.
    ARTIFICIAL NEURON MODEL
    Inputs to the network are represented by the
    x1
    mathematical symbol, xn w1

    Each of these inputs are multiplied by a w2 f(w1 x1 + + wnxn)


    connection weight , wn x2
    f
    sum = w1 x1 + + wnxn
    These products are simply summed, fed
    through the transfer function, f( ) to generate wn
    a result and then output. xn
    ANALOGY

    Biological Terminology Artificial Neural Network


    Terminology

    Neuron Node/Unit/Cell/Neurode

    Synapse Connection/Edge/Link

    Synaptic Efficiency Connection Strength/Weight

    Firing frequency Node output


    ARTIFICIAL NEURAL NETWORK
    Artificial Neural Network (ANNs) are programs designed to solve
    any problem by trying to mimic the structure and the function of our
    nervous system.
    Neural networks are based on simulated neurons, Which are joined
    together in a variety of ways to form networks.
    Neural network resembles the human brain in the following two
    ways: -
    * A neural network acquires knowledge through learning.
    *A neural networks knowledge is stored within the
    interconnection strengths known as synaptic weight.
    CONTD

    ARTIFICIAL NEURAL NETWORK MODEL

    Hidden layers

    connections Desired
    output
    Neural network
    Input Including Actual
    output layer connections output output
    (called weights) Comp
    between neuron are

    Input layer

    Fig 1 : artificial neural network model Figure showing adjust of neural network
    LEARNING
    Neurons in an animals brain are hard wired. It is equally obvious that
    animals, especially higher order animals, learn as they grow.
    How does this learning occur?
    What are possible mathematical models of learning?
    In artificial neural networks, learning refers to the method of modifying
    the weights of connections between the nodes of a specified network.
    The learning ability of a neural network is determined by its
    architecture and by the algorithmic method chosen for training.
    CONTD

    SUPERVISED LEARNING UNSUPERVISED LEARNING

    A teacher is available to indicate This is learning by doing.


    whether a system is performing In this approach no sample
    correctly, or to indicate the amount of outputs are provided to the
    error in system performance. Here a
    teacher is a set of training data. network against which it can
    The training data consist of pairs of measure its predictive
    input and desired output values that performance for a given vector of
    are traditionally represented in data inputs.
    vectors. One common form of
    Supervised learning can also be unsupervised learning is
    referred as classification, where we clustering where we try to
    have a wide range of classifiers, categorize data in different
    (Multilayer perceptron, k nearest clusters by their similarity.
    neighbor..etc)
    THE BACKPROPAGATION ALGORITHM

    The backpropagation algorithm (Rumelhart and McClelland, 1986) is


    used in layered feed-forward Artificial Neural Networks.
    Back propagation is a multi-layer feed forward, supervised learning
    network based on gradient descent learning rule.
    we provide the algorithm with examples of the inputs and outputs we
    want the network to compute, and then the error (difference between
    actual and expected results) is calculated.
    The idea of the backpropagation algorithm is to reduce this error,
    until the Artificial Neural Network learns the training data.
    The activation function of the artificial neurons in ANNs
    implementing the backpropagation algorithm is a
    weighted sum (the sum of the inputs xi multiplied by their
    respective weights wji) Inputs, x

    output
    The most common output function is the sigmoidal
    function:

    Since the error is the difference between the actual and


    the desired output, the error depends on the weights, and
    we need to adjust the weights in order to minimize the
    error. We can define the error function for the output of Weights, v weights, w
    each neuron:
    Fig: Basic Block of
    Back propagation neural network
    NEURAL NETWORK
    APPLICATIONS
    ADVANTAGES
    It involves human like thinking.
    They handle noisy or missing data.
    They can work with large number of variables or parameters.
    They provide general solutions with good predictive accuracy.
    System has got property of continuous learning.
    They deal with the non-linearity in the world in which we live.
    CONCLUSION

    You might also like