Scribd Logo
Upload

Welcome to Scribd!

  • 26 views

    Hedlin Novian Napitupulu Tugas3

    Uploaded by

    hedlinbarcelona10 hedlin
    The document describes a feedforward neural network model for predicting whether a customer will buy a computer. It includes a dataset of 5 customers with 4 input features and the target output. The neural network has 3 input nodes, 3 hidden nodes, and 1 output node. The hidden layer weights are initialized to 0.3 and the output layer weights to 0.7. One epoch of backpropagation is then performed on the network using the tensor approach to calculate the gradients and update the weights.

    Copyright:

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

    Hedlin Novian Napitupulu Tugas3

    Uploaded by

    hedlinbarcelona10 hedlin
    26 views7 pages
    The document describes a feedforward neural network model for predicting whether a customer will buy a computer. It includes a dataset of 5 customers with 4 input features and the target output. The neural network has 3 input nodes, 3 hidden nodes, and 1 output node. The hidden layer weights are initialized to 0.3 and the output layer weights to 0.7. One epoch of backpropagation is then performed on the network using the tensor approach to calculate the gradients and update the weights.

    Original Description:

    fefeff

    Original Title

    1462000239_hedlin novian napitupulu tugas3

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    The document describes a feedforward neural network model for predicting whether a customer will buy a computer. It includes a dataset of 5 customers with 4 input features and the target output. The neural network has 3 input nodes, 3 hidden nodes, and 1 output node. The hidden layer weights are initialized to 0.3 and the output layer weights to 0.7. One epoch of backpropagation is then performed on the network using the tensor approach to calculate the gradients and update the weights.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    26 views7 pages

    Hedlin Novian Napitupulu Tugas3

    Uploaded by

    hedlinbarcelona10 hedlin
    The document describes a feedforward neural network model for predicting whether a customer will buy a computer. It includes a dataset of 5 customers with 4 input features and the target output. The neural network has 3 input nodes, 3 hidden nodes, and 1 output node. The hidden layer weights are initialized to 0.3 and the output layer weights to 0.7. One epoch of backpropagation is then performed on the network using the tensor approach to calculate the gradients and update the weights.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    You are on page 1of 7

    Disusun oleh:

    Hedlin novian napitupulu 14620000239

    Dosen Pengampu:

    Andrey Kartika Widhy Hapantenda, S. Kom., M. Kom.

    FAKULTAS TEKNIK

    PROGRAM STUDI INFORMATIKA

    UNIVERSITAS 17 AGUSTUS 1945 SURABAYA

    2023
    Tugas : Feedforward Neural Network .

    data pembelajaran
    Credit
    Income Student Buys computer
    rating
    1 1 0 1
    2 0 1 0
    0 1 2 0
    1 0 0 1
    0 0 0 1
    Keterangan :

    • Buys computer : no 0, yes 1


    • Income : low  0, Medium  1, High  2
    • Strudent : no  0, yes  1
    • Credit rating : fair  0, Average  1, Good  2, Excellent  3
    • Nilai threshold setiap neuron = 1
    • Nilai bobot input layer ke hidden layer = 0,3
    • Nilai bobot hidden layer ke output layer = 0,7
    1. Gambarkan jaringannya lengkap dengan nilai threshold dan bobotnya ?

    Diketahhui :

    • = 0,1
    • threshold neuron 4 = 1
    • threshold neuron 5 = 1
    • threshold neuron 6 = 1
    • threshold neuron 7 = 1

    initial weight

    untuk neuron :

    • hidden neuron 4 : w14 =0,3 ; w24=0,3 ; w34 = 0,3


    • hidden neuron 5 : w15 =0,3 ; w25=0,3 ; w35 = 0,3
    • hidden neuron 6 : w16 =0,3 ; w26=0,3 ; w36 = 0,3
    • hidden neuron 7 : w47 =0,7 ; w57=0,9 ; w67 = 0,9
    2. Lakukan proses pembelajaran dengan backpropagation sebanyak 1
    epoch menggunakan dataset pada table dengan pendekatan tensor
    > input to hidden layer (feed forward)

    o = σ(x input * w input + θ)

    = σ 1 1 0 * 0,3 0,3 0,3 + 1 1 1


    2 0 1 0,3 0,3 0,3
    0 1 2 0,3 0,3 0,3
    1 0 0
    0 0 0

    +
    = σ 0,6 0,6 0,6 1 1 1
    0,9 0,9 0,9 1 1 1
    0,9 0,9 0,9 1 1 1
    0,3 0,3 0,3 1 1 1
    0 0 0 1 1 1

    = σ 1,6 1,6 1,6


    1,9 1,9 1,9
    1,9 1,9 1,9
    1,3 1,3 1,3
    1 1 1

    o= σ 1,6 1,6 1,6


    nilai mutlak 1,9 1,9 1,9
    1,9 1,9 1,9
    6

    1,3 1,3 1,3


    1 1 1

    > Output to hidden

    δ = ( y - v ) - (v.transpose)( 1 - v )

    δ= 0 - 6,88 * 6,88 8,77 8,77 4,99 3,1 * 1


    3 8,77 1
    3 8,77 1
    1 4,99 1
    0 3,1 1

    δ= -6,88 * 4,36 5,44 5,44 3,28 2,2 * -5,88


    -5,77 -7,77
    -5,77 -7,77
    -3,99 -3,99
    -3,1 -2,1

    δ= -6,88 * -25,64 -42,27 -42,27 -13,09 -4,62


    -5,77
    -5,77
    -3,99
    -3,1
    7

    δ= -6,88 * -127,88
    -5,77
    -5,77
    -3,99
    -3,1

    You might also like