An artificial neural network consists of only two layers. Three neurons are in the input layer and (0.1' one in the output layer. The initial weights are w =( 0.1 \0.1. Use the following algorithm to determine the new weights after one iteration for an input x = (9.0) 6.0 if the desired output is 0. 1 Use f(net)= 1+ net = Ex,w. %3D %3D - net e Let the learning factor } = 1.0 Solution: 1- Calculate the actual output actual _output =f(net) = %3D 2- Calculate the differentiation of f (net) at the output neuron f(net) =f(net) (1-f(net)) = 3- Calculate the error term at the output neuron 8 = (desired – actual _output)'f (net) = 4- Update the weights (there are 3 weights to be updated) AW=G * input * 8 Wnew = Wold+AW

Computer Networking: A Top-Down Approach (7th Edition)
7th Edition
ISBN:9780133594140
Author:James Kurose, Keith Ross
Publisher:James Kurose, Keith Ross
Chapter1: Computer Networks And The Internet
Section: Chapter Questions
Problem R1RQ: What is the difference between a host and an end system? List several different types of end...
icon
Related questions
Question

Question:

 

An artificial neural network consists of only two layers. Three neurons are in the input layer and
(0.1'
one in the output layer. The initial weights are w =
\0.1/
0.1
Use the following algorithm to determine the new weights after one iteration for an input x =
19.0
6.0 ) if the desired output is 0.
\1.0,
1
Use f(net) =
Ex.w
net =
1+e-net
Let the learning factor } = 1.0
Solution:
1- Calculate the actual output
actual_output =f(net) =
2- Calculate the differentiation of f (net) at the output neuron
f (net) =f(net) (1-f(net)) =
3- Calculate the error term at the output neuron
8 = (desired – actual_output) f (net) =
4- Update the weights (there are 3 weights to be updated) AW=5 * input * 8
Wnew = Wold + AW
Transcribed Image Text:An artificial neural network consists of only two layers. Three neurons are in the input layer and (0.1' one in the output layer. The initial weights are w = \0.1/ 0.1 Use the following algorithm to determine the new weights after one iteration for an input x = 19.0 6.0 ) if the desired output is 0. \1.0, 1 Use f(net) = Ex.w net = 1+e-net Let the learning factor } = 1.0 Solution: 1- Calculate the actual output actual_output =f(net) = 2- Calculate the differentiation of f (net) at the output neuron f (net) =f(net) (1-f(net)) = 3- Calculate the error term at the output neuron 8 = (desired – actual_output) f (net) = 4- Update the weights (there are 3 weights to be updated) AW=5 * input * 8 Wnew = Wold + AW
Expert Solution
trending now

Trending now

This is a popular solution!

steps

Step by step

Solved in 5 steps

Blurred answer
Similar questions
  • SEE MORE QUESTIONS
Recommended textbooks for you
Computer Networking: A Top-Down Approach (7th Edi…
Computer Networking: A Top-Down Approach (7th Edi…
Computer Engineering
ISBN:
9780133594140
Author:
James Kurose, Keith Ross
Publisher:
PEARSON
Computer Organization and Design MIPS Edition, Fi…
Computer Organization and Design MIPS Edition, Fi…
Computer Engineering
ISBN:
9780124077263
Author:
David A. Patterson, John L. Hennessy
Publisher:
Elsevier Science
Network+ Guide to Networks (MindTap Course List)
Network+ Guide to Networks (MindTap Course List)
Computer Engineering
ISBN:
9781337569330
Author:
Jill West, Tamara Dean, Jean Andrews
Publisher:
Cengage Learning
Concepts of Database Management
Concepts of Database Management
Computer Engineering
ISBN:
9781337093422
Author:
Joy L. Starks, Philip J. Pratt, Mary Z. Last
Publisher:
Cengage Learning
Prelude to Programming
Prelude to Programming
Computer Engineering
ISBN:
9780133750423
Author:
VENIT, Stewart
Publisher:
Pearson Education
Sc Business Data Communications and Networking, T…
Sc Business Data Communications and Networking, T…
Computer Engineering
ISBN:
9781119368830
Author:
FITZGERALD
Publisher:
WILEY