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

Welcome to Scribd!

  • Multi: 9: For in A

    Uploaded by

    sadek sadek
    11 views5 pages
    The document provides instructions for performing one step of backpropagation for training a multi-layer neural network with a hidden layer and output layer using sigmoid activation functions. The learning rate is 0.1. Equations are provided for calculating the errors and weight updates for each layer.

    Original Description:

    AI course

    Original Title

    6

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    Report this Document
    The document provides instructions for performing one step of backpropagation for training a multi-layer neural network with a hidden layer and output layer using sigmoid activation functions. The learning rate is 0.1. Equations are provided for calculating the errors and weight updates for each layer.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Flag for inappropriate content
    Download as pdf or txt
    11 views5 pages

    Multi: 9: For in A

    Uploaded by

    sadek sadek
    The document provides instructions for performing one step of backpropagation for training a multi-layer neural network with a hidden layer and output layer using sigmoid activation functions. The learning rate is 0.1. Equations are provided for calculating the errors and weight updates for each layer.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Flag for inappropriate content
    Download as pdf or txt
    of 5

    ,,J.

    l:

    9: For multi layer neural networks shown in ligure below. Perform a one_ step
    backpropagation training (forward and backward phases) using the learning raG-is 0.1
    assume neurons in the hidden layer and output layer have nonlinear signroid function
    ( unipola r).

    u2

    t
    I
    t
    F*fr r.*",1 fo, hl .lJerft L*luy
    nd:'= L*jiX; + #i
    #l -- Lt's
    nelt -- Z.d*l + ()'?i6 I + 1.1

    nelL r-c>,+ ,6[ + l'516 I + (-o,l f t) = z'l

    ()J -- F tr,*lf ) --
    t + AnLll'

    Q') l+ e-r,f,S '


    =

    Cz E,
    ,

    l+e
    @ forrarorJ for D/p tAJw
    ,{_-_
    rterl €w4j Oj
    nctt -: {,zl(" o.qffi+ ('o'\ # o.gql) +0,5)ft =l,Lllg
    I
    o,8l
    ^l,qlq =
    l+e

    o*sj =Dsp oj
    )
    - t,1lq

    >t c o.o3l

    UJtt *-, \. -
    f.

    -t {r*l fi c2,o$ t

    = *o.j f o*l * a ro 3l -
    ll-

    tilt'?-
    tNli % elL5.*& d.J-* o. o 3 I
    ilr
    k" h:Jolun-

    t^*'r'C rtielu) = {tJ'iLotd) +


    AwJ,'a :l Bj'o;
    5j d- -->F LS{ j
    t)
    bwul l<

    (o.o3t X f.L) o. otroY


    (,
    =
    _ *l
    c, - (3o o89 t

    Wtl a Z. € + ,er 1"'# o. ooo L.,f * 1 €'

    ttllL€ o.L + o'l -X o'c2ooL1 )A I u


    & I ,
    t:UtZa I + Qtt X ot@oo\
    4 1=
    WLi = e,] + e, 7 X o,Ga abql
    -* lt-
    Wt* l' 5 + o' 7 -* o* ooo Eqt

    Ie
    wL\- r€,.1+ o.{ 4 ot ooa sqt '*
    _r
    \i rln v\ L \.1 a-. .-1 ( \ {\'., {>'*\* r j

    \ -{r
    "}
    \ r*') 'r {ta*) s
    .--t-\ i'*-' ,^i ,- \,. '. \-(L o* \

    ,l,L ) d^{ ({1 t [,.-C. f ,b";a


    )

    \
    L ^T
    _C
    i-
    + icx):
    t:

    x-\
    \- -.te
    tJ\
    \
    /
    \ \l rr * Q._,\o 1 )
    ,,
    - (-/' )

    Lt -+
    qcx) :

    ) a^(
    tJ
    eAt [,-.c. lr"n,

    x -f' \
    L'*e- +F.*)=\ T

    u)

    Scanned by CamScanner

    You might also like