Scribd
Upload
66 views

Back Propagation Example

This document provides an example of backpropagation in a neural network with two inputs, one hidden layer, and three outputs. It asks the reader to: 1) Calculate the values of all nodes in the network given specific input values. 2) Calculate how the weights would change using backpropagation, given the same input values and desired output values. Temporary variables can be used but must be defined in terms of the original variables.

Uploaded by

Raghunath Siripudi
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
66 views

Back Propagation Example

This document provides an example of backpropagation in a neural network with two inputs, one hidden layer, and three outputs. It asks the reader to: 1) Calculate the values of all nodes in the network given specific input values. 2) Calculate how the weights would change using backpropagation, given the same input values and desired output values. Temporary variables can be used but must be defined in terms of the original variables.

Uploaded by

Raghunath Siripudi
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 3

Back-Propagation-Example

Question 1
O1 6 O2 6 O3 6
'$ '$ '$

V1 V2 V3
&% &% &%
BMB 6 
B 
w3 B w4  w5
B 

'$
B
B 

7
&%
]
J
 J
w1  J w2
'$
 '$
J

x1 x2
&% &%

The above neural network has two layers (one hidden layer), two inputs, and three outputs. (There are NO
bias connections.) All nodes compute the sigmoid function with β = 1.
A.1 Give explicit expressions to the values of all nodes in forward propagation when the network is given
the input x1 = 3, x2 = 9, with the desired output y1 = 1, y2 = 0,y3 = 1. Your answer should be in terms of
the old weights w1 , w2 , w3 , w4 , w5 . You may use the notation S(.) instead of explicitly computing sigmoid
values.

Answer

V =

V1 =

V2 =

V3 =

O1 =

O2 =

O3 =
A.2 Give explicit expressions to how the weights change by back propagation when the network is given
the same example as above. Use  = 0.1.
Your answer should be in terms of the old weights w1 , w2 , w3 , w4 , w5 and the node values V , V1 , V2 ,
V3 , O1 , O2 , O3 , that were computed in A.1. You may use the notation S(.) instead of explicitly computing
sigmoid values. You may use temporary variables in your answer, but make sure that they are defined in
terms of the above variables.

Answer I am using the following temporary variables in my answer:

Answer

new w1 =

new w2 =

new w3 =

new w4 =

new w5 =

You might also like