Scribd
Upload
2 views

Function Approximation

Uploaded by

akshat112004
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOC, PDF, TXT or read online on Scribd
2 views

Function Approximation

Uploaded by

akshat112004
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOC, PDF, TXT or read online on Scribd
You are on page 1/ 1

Consider the simple, single-input, single-output neural network shown

in Figure 1 below. Assuming sigmoidal hidden-unit and linear output-


unit activation functions what values of the weights will approximate
the function in Figure 2?

Figure 1 Figure 2

We can represent the given function in terms of the hard limiting functions (or threshold
activation functions-unipolar). Remember this we studied in Network Theory.

Recognizing that the threshold function can be approximated arbitrarily well by a


sigmoid function when is very large ( ), we can write

where denotes sigmoid and is a very high value. Now we can


write the given function in terms of sigmoidal activation functions.

for large

The output of the neural network shown in Figure 1 is

Compare this and the previous equation

, ….. so on. (You can also find another set of possible weight
values).

You might also like