Scribd Logo
Upload

Welcome to Scribd!

  • 39 views

    Artificial Neural Networks - : Introduction

    Uploaded by

    Sangeeta Tiwari
    Artificial neural networks are modeled after biological neurons and are composed of interconnected artificial neurons that can learn patterns from data. Neural networks can be trained to perform classification tasks by minimizing an energy function that measures error. Simple neural networks like perceptrons use a single layer while multi-layer perceptrons use multiple hidden layers to represent more complex decision boundaries. Neural networks are applied to tasks like object recognition, prediction, and control.

    Copyright:

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

    Artificial Neural Networks - : Introduction

    Uploaded by

    Sangeeta Tiwari
    39 views20 pages
    Artificial neural networks are modeled after biological neurons and are composed of interconnected artificial neurons that can learn patterns from data. Neural networks can be trained to perform classification tasks by minimizing an energy function that measures error. Simple neural networks like perceptrons use a single layer while multi-layer perceptrons use multiple hidden layers to represent more complex decision boundaries. Neural networks are applied to tasks like object recognition, prediction, and control.

    Original Description:

    Ann

    Original Title

    Ann

    Copyright

    © © All Rights Reserved

    Available Formats

    PPT, PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    Artificial neural networks are modeled after biological neurons and are composed of interconnected artificial neurons that can learn patterns from data. Neural networks can be trained to perform classification tasks by minimizing an energy function that measures error. Simple neural networks like perceptrons use a single layer while multi-layer perceptrons use multiple hidden layers to represent more complex decision boundaries. Neural networks are applied to tasks like object recognition, prediction, and control.

    Copyright:

    © All Rights Reserved
    Download as PPT, PDF, TXT or read online from Scribd
    Download as ppt, pdf, or txt
    39 views20 pages

    Artificial Neural Networks - : Introduction

    Uploaded by

    Sangeeta Tiwari
    Artificial neural networks are modeled after biological neurons and are composed of interconnected artificial neurons that can learn patterns from data. Neural networks can be trained to perform classification tasks by minimizing an energy function that measures error. Simple neural networks like perceptrons use a single layer while multi-layer perceptrons use multiple hidden layers to represent more complex decision boundaries. Neural networks are applied to tasks like object recognition, prediction, and control.

    Copyright:

    © All Rights Reserved
    Download as PPT, PDF, TXT or read online from Scribd
    Download as ppt, pdf, or txt
    You are on page 1of 20

    Artificial Neural Networks

    - Introduction -
    Overview

    1. Biological inspiration
    2. Artificial neurons and neural networks
    3. Application
    Biological Neuron
    Animals are able to react adaptively to changes in their
    external and internal environment, and they use their nervous
    system to perform these behaviours.
    An appropriate model/simulation of the nervous system
    should be able to produce similar responses and behaviours in
    artificial systems.
    Biological Neuron

    The information transmission happens at the synapses.


    Artificial neurons Neuron
    Artificial neurons

    x1
    x2 w1
    n Output
    x3 w2 z   wi xi ; y  H ( z )
    Inputs

    i 1 y
    … w3
    ..
    xn-1 . wn-1
    xn wn
    one possible model
    Artificial neurons

    Nonlinear generalization of neuron:

    y  f ( x, w)
    y is the neuron’s output, x is the vector of inputs, and w
    is the vector of synaptic weights.
    Examples: 1
    y w xa
    sigmoidal neuron
    1 e
    T

    || x  w||2

    ye 2a 2 Gaussian neuron
    Other Model
    Hopfield Retropropagation
    From Logical Neurons to Finite Automata
    1
    AND 1.5

    1
    OR 0.5

    NOT
    0
    -1
    Artificial neural networks

    Output
    Inputs

    An artificial neural network is composed of many artificial


    neurons that are linked together according to a specific
    network architecture. The objective of the neural network
    is to transform the inputs into meaningful outputs.
    Artificial neural networks

    Tasks to be solved by artificial neural networks:


    • controlling the movements of a robot based on self-
    perception and other information (e.g., visual
    information);
    • deciding the category of potential food items (e.g.,
    edible or non-edible) in an artificial world;
    • recognizing a visual object (e.g., a familiar face);
    • predicting where a moving object goes, when a robot
    wants to catch it.
    Neural network mathematics

    Output
    Inputs

    y11  f ( x1 , w11 )  y11  2


      y1  f ( y1 , w12 )  y 2

    y 2  f ( x 2 , w2 ) y 1   y 2  2
    1 1 1  3

     y 2  f ( y , w2 )
    1 2 2
      2
     y  f ( y 2
    , w3
    1)
    1
    y y 3 Out
    y 31  f ( x3 , w31 )  y3  2  2 
    1  y3  f ( y , w3 )

    1 2
     y3 
    y 14  f ( x 4 , w14 )  y4 
    Neural network mathematics

    Neural network: input / output transformation

    yout  F ( x,W )

    W is the matrix of all weight vectors.


    Learning principle for
    artificial neural networks
    ENERGY MINIMIZATION

    We need an appropriate definition of energy for artificial


    neural networks, and having that we can use
    mathematical optimisation techniques to find how to
    change the weights of the synaptic connections between
    neurons.

    ENERGY = measure of task performance error


    Perceptron application
    y  1
    +
    ++
    + +
    + +
    + + + ++ +
    +
    + + +
    + + ++ +
    + + + + ++
    + +
    + +
    y  1 + +
    ++
    y  sign (v)
    c0  c1 x1  c2 x2  0
     v  c0  c1 x1  c2 x2
    c0 c2
    c1
    x1
    1 x2
    Multi-Layer Perceptron
    • One or more hidden
    layers
    Output layer • Sigmoid activations
    functions
    2nd hidden
    layer

    1st hidden
    layer

    Input data
    Multi-Layer Perceptron Application

    Types of Result
    Structure
    Decision Regions
    Single-Layer Half Plane A B
    Bounded By
    Hyperplane B A

    Two-Layer Convex Open A B


    Or
    Closed Regions B A

    Three-Layer Abitrary
    A B
    (Complexity
    Limited by No.
    B A
    of Nodes)
    Conclusion

    NN have some desadvantages such as:

    1. Preprocessing
    2. Results interpretation by high dimension
    3. Learning phase/Supervised/Non
    Supervised
    References
    1. http://neuron.eng.wayne.edu/software.html
    Many useful example.
    2. http://ieee.uow.edu.au/~daniel/software/libn
    eural/BPN_tutorial/BPN_English/BPN_Engli
    sh/BPN_English.html
    3. http://www.ai-junkie.com/
    4. http://diwww.epfl.ch/mantra/tutorial/english/
    Demo: OCR

    You might also like