Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Scribd Logo
Upload

Welcome to Scribd!

  • 31 views

    Introduction To Neural Networks: Freek Stulp

    Uploaded by

    meenakshi sharma
    This document introduces three classes of neural networks: perceptrons, multi-layer feedforward networks, and recurrent networks. Perceptrons are the simplest neural networks but cannot represent complex functions. Multi-layer feedforward networks can represent complex non-linear functions using multiple hidden layers and backpropagation learning. Recurrent networks allow connections between units in different layers but are more difficult to train than feedforward networks.

    Copyright:

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

    Introduction To Neural Networks: Freek Stulp

    Uploaded by

    meenakshi sharma
    31 views12 pages
    This document introduces three classes of neural networks: perceptrons, multi-layer feedforward networks, and recurrent networks. Perceptrons are the simplest neural networks but cannot represent complex functions. Multi-layer feedforward networks can represent complex non-linear functions using multiple hidden layers and backpropagation learning. Recurrent networks allow connections between units in different layers but are more difficult to train than feedforward networks.

    Original Title

    inn.ppt

    Copyright

    © © All Rights Reserved

    Available Formats

    PPT, PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    This document introduces three classes of neural networks: perceptrons, multi-layer feedforward networks, and recurrent networks. Perceptrons are the simplest neural networks but cannot represent complex functions. Multi-layer feedforward networks can represent complex non-linear functions using multiple hidden layers and backpropagation learning. Recurrent networks allow connections between units in different layers but are more difficult to train than feedforward networks.

    Copyright:

    © All Rights Reserved
    Download as PPT, PDF, TXT or read online from Scribd
    Download as ppt, pdf, or txt
    31 views12 pages

    Introduction To Neural Networks: Freek Stulp

    Uploaded by

    meenakshi sharma
    This document introduces three classes of neural networks: perceptrons, multi-layer feedforward networks, and recurrent networks. Perceptrons are the simplest neural networks but cannot represent complex functions. Multi-layer feedforward networks can represent complex non-linear functions using multiple hidden layers and backpropagation learning. Recurrent networks allow connections between units in different layers but are more difficult to train than feedforward networks.

    Copyright:

    © All Rights Reserved
    Download as PPT, PDF, TXT or read online from Scribd
    Download as ppt, pdf, or txt
    of 12

    Introduction to

    Neural Networks
    Freek Stulp
    Overview
    Biological Background
    Artificial Neuron
    Classes of Neural Networks
    1. Perceptrons
    2. Multi-Layered Feed-Forward Networks
    3. Recurrent Networks
    Conclusion

    2
    Biological Background
    Neuron consists of:
     Cell body
     Dendrites
     Axon
     Synapses

    Neural activation :
     Throught dendrites/axon
     Synapses have different
    strengths

    3
    Artificial Neuron
    Input links Unit Output links
    (dendrites) (cell body) (axon)

    aj Wji
    ini = ai =
    ai
    SajWji g(ini)

    4
    Class I: Perceptron

    Ij Wj O

    -1 W0
    W1 in = a=
    a1 a
    W2 SajWj g(in)
    a2

    a = g(-W0 + W1a1 + W2a2) { 0, in<0


    g(in) = 1, in>0

    5
    Learning in Perceptrons
    Perceptrons can learn mappings Example: boolean OR
    from inputs I to outputs O by
    changing weights W D: d I T
    0 00 0
    Training set D: 1 01 1
     Inputs: I0, I1 ... In 2 10 1
     Targets: T0, T1 ...Tn 3 11 1

    Output O of network is
    not necessary equal to T!

    6
    Learning in Perceptrons
    Error often defined as:
    E(W) = 1/2SdD(td-od)2

    Go towards the minimum error!

    Update rules:
     wi = wi + Dwi
     Dwi = -hdE/dwi
     dE/dwi = d/dwi 1/2SdD(td-od)2

    = SdD(td-od)iid i
    This is called gradient descent

    7
    Class II: Multi-layer
    Feed-forward Networks
    Multiple layers:
     hidden layer(s)
    Input Hidden Output

    Feed-forward:
     Output links only connected
    to input links in the next
    layer

    Complex non-linear
    functions can be
    represented

    8
    Learning in MLFF Networks
    For output layer, weight updating similar to
    perceptrons.
    Problem: What are the errors in the hidden layer?
    Backpropagation Algorithm
     For each hidden layer (from output to input):
     For each unit in the layer determine how much it contributed to
    the errors in the previous layer.
     Adapt the weight according to this contribution

    This is also gradient descent

    9
    Class III: Recurrent Networks
    No restrictions on
    Input Hidden Output
    connections

    Behaviour more
    difficult to predict/
    understand

    10
    Conclusion
    Inspiration from biology, though artificial brains
    are still very far away.

    Perceptrons too simple for most problems.

    MLFF Networks good as function approximators.


     Many of your articles use these networks!

    Recurrent networks complex but useful too.

    11
    Literature

    Artificial Intelligence: A Modern Approach


     Stuart Russel and Peter Norvig

    Machine Learning
     Tom M. Mitchell

    12

    You might also like