Scribd Logo
Upload

Welcome to Scribd!

  • 17 views

    Input Output Desired Output X0 X1 X2 W0 W1 W2 Net y 1 0 0 1 1 1 1 1 0 1 0 1 0.5 1 1 1.5 1 0 1 1 0 0 1 0.5 1 1 0 1 1 1 - 0.5 0.5 0.5 0.5 1 1

    Uploaded by

    Fikri Basa
    The document describes a neural network undergoing training over 4 epochs to classify inputs. It shows the initial weights, inputs, target outputs, calculated network outputs, and updated weights at each epoch as the network learns the relationships in the training data through backpropagation and weight updates. The network weights converge by the final epoch so the network accurately classifies all inputs in the training set.

    Copyright:

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

    Input Output Desired Output X0 X1 X2 W0 W1 W2 Net y 1 0 0 1 1 1 1 1 0 1 0 1 0.5 1 1 1.5 1 0 1 1 0 0 1 0.5 1 1 0 1 1 1 - 0.5 0.5 0.5 0.5 1 1

    Uploaded by

    Fikri Basa
    17 views4 pages
    The document describes a neural network undergoing training over 4 epochs to classify inputs. It shows the initial weights, inputs, target outputs, calculated network outputs, and updated weights at each epoch as the network learns the relationships in the training data through backpropagation and weight updates. The network weights converge by the final epoch so the network accurately classifies all inputs in the training set.

    Original Description:

    Artificial Intelegent

    Original Title

    Delta Rule

    Copyright

    © © All Rights Reserved

    Available Formats

    XLSX, PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    The document describes a neural network undergoing training over 4 epochs to classify inputs. It shows the initial weights, inputs, target outputs, calculated network outputs, and updated weights at each epoch as the network learns the relationships in the training data through backpropagation and weight updates. The network weights converge by the final epoch so the network accurately classifies all inputs in the training set.

    Copyright:

    © All Rights Reserved
    Download as XLSX, PDF, TXT or read online from Scribd
    Download as xlsx, pdf, or txt
    17 views4 pages

    Input Output Desired Output X0 X1 X2 W0 W1 W2 Net y 1 0 0 1 1 1 1 1 0 1 0 1 0.5 1 1 1.5 1 0 1 1 0 0 1 0.5 1 1 0 1 1 1 - 0.5 0.5 0.5 0.5 1 1

    Uploaded by

    Fikri Basa
    The document describes a neural network undergoing training over 4 epochs to classify inputs. It shows the initial weights, inputs, target outputs, calculated network outputs, and updated weights at each epoch as the network learns the relationships in the training data through backpropagation and weight updates. The network weights converge by the final epoch so the network accurately classifies all inputs in the training set.

    Copyright:

    © All Rights Reserved
    Download as XLSX, PDF, TXT or read online from Scribd
    Download as xlsx, pdf, or txt
    You are on page 1of 4

    input output desired output

    X0 X1 X2 W0 W1 W2 net y
    1 0 0 1 1 1 1 1 0
    1 0 1 0.5 1 1 1.5 1 0
    1 1 0 0 1 0.5 1 1 0
    1 1 1 -0.5 0.5 0.5 0.5 1 1
    change learning coef
    W0 W1 w2
    -0.5 0 0 0.5
    -0.5 0 -0.5
    -0.5 -0.5 0
    0 0 0
    Jaringan Syaraf Tiruan : Delta Ru

    Epoch 1
    input Bobot Awal
    target output (t) Net (a)
    X1 X2 W1 W2
    0 0 0 0.1 0.3 0
    0 1 1 0.1 0.3 0.3
    1 0 1 0.1 0.5 0.1
    1 1 1 0.3 0.5 0.8

    Epoch 2
    input Bobot Awal
    target output (t) Net (a)
    X1 X2 W1 W2
    0 0 0 0.3 0.5 0
    0 1 1 0.3 0.5 0.5
    1 0 1 0.3 0.7 0.3
    1 1 1 0.5 0.7 1.2

    epoch 3
    input Bobot Awal
    target output (t) Net (a)
    X0 X1 X2 W1 W2
    0 0 0 0.5 0.7 0
    0 1 1 0.5 0.7 0.7
    1 0 1 0.5 0.7 0.5
    1 1 1 0.7 0.7 1.4

    epoch 4
    input Bobot Awal
    target output (t) Net (a)
    X1 X2 W1 W2
    0 0 0 0.7 0.7 0
    0 1 1 0.7 0.7 0.7
    1 0 1 0.7 0.7 0.7
    1 1 1 0.7 0.7 1.4
    n Syaraf Tiruan : Delta Rule

    Change (Bobot Akhir)


    Fungsi Aktivasi (y>0,5) Error () learning rate
    W0 W1 w2
    0 0 0.1 0.3 0.2
    0 1 0.1 0.5
    0 1 0.3 0.5
    1 0 0.3 0.5

    Change (Bobot Akhir)


    Fungsi Aktivasi (y>0,5) Error ()
    W0 W1 w2
    0 0 0.3 0.5
    0 1 0.3 0.7
    0 1 0.5 0.7
    1 0 0.5 0.7

    Change (Bobot Akhir)


    Fungsi Aktivasi (y>0,5) Error ()
    W0 W1 w2
    0 0 0.5 0.7
    1 0 0.5 0.7
    0 1 0.7 0.7
    1 0 0.7 0.7

    Change (Bobot Akhir)


    Fungsi Aktivasi (y>0,5) Error ()
    W0 W1 w2
    0 0 0.7 0.7
    1 0 0.7 0.7
    1 0 0.7 0.7
    1 0 0.7 0.7

    You might also like

    pFad - Phonifier reborn

    Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

    Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


    Alternative Proxies:

    Alternative Proxy

    pFad Proxy

    pFad v3 Proxy

    pFad v4 Proxy