Solution of multi-layer ann with sigmoid units, Computer Engineering

Solution of multi-layer ann with sigmoid units:

Assume here that we input the values 10, 30, 20 with the three input units and from top to bottom. So after then the weighted sum coming into H1 will be as: 

SH1 = (0.2 * 10) + (-0.1 * 30) + (0.4 * 20) = 2 -3 + 8 = 7. 

After then the σ function is applied to SH1 to give as: 

σ(SH1) = 1/(1+e-7) = 1/(1+0.000912) = 0.999 

Here don't forget to negate S. Also the weighted sum coming into H2 will be as: 

SH2 = (0.7 * 10) + (-1.2 * 30) + (1.2 * 20) = 7 - 36 + 24 = -5 

Now next σ applied to SH2 gives as: 

σ(SH2) = 1/(1+e5) = 1/(1+148.4) = 0.0067 

Furthermore from this we can see there that H1 has fired, but H2 has not. So now we can calculate the weights sum going in to output in unit O1 will be as: 

SO1 = (1.1 * 0.999) + (0.1*0.0067) = 1.0996 

And here next the weighted sum going in to output in unit O2 will be as: 

SO2 = (3.1 * 0.999) + (1.17*0.0067) = 3.1047 

However the output sigmoid unit in O1 will now calculate the output values from the network for O1 as:

 σ(SO1) = 1/(1+e-1.0996) = 1/(1+0.333) = 0.750 

and the output from the network for O2: 

σ(SO2) = 1/(1+e-3.1047) = 1/(1+0.045) = 0.957 

However therefore if this network represented the learned rules for a categorisation problem then the input triple (10,30,20) would be categorised into the category associated with O2 it means it has the larger output.

Posted Date: 1/11/2013 7:14:06 AM | Location : United States







Related Discussions:- Solution of multi-layer ann with sigmoid units, Assignment Help, Ask Question on Solution of multi-layer ann with sigmoid units, Get Answer, Expert's Help, Solution of multi-layer ann with sigmoid units Discussions

Write discussion on Solution of multi-layer ann with sigmoid units
Your posts are moderated
Related Questions
explain network operating system and design issues?

What is XMS Memory system is divided into 3 main parts. TPA (transient program area), system area and XMS (extended memory system). Type of microprocessor in your computer sign

What are disadvantages of EPROM? The chip must be physically removed from the circuit for reprogramming and its whole contents are erased by the UV light.

Q. Show the Simple Arithmetic Application? The question is why can't we simply employ XCHG instruction with 2 memory variables as operand? To answer the question let's look int

What is hit? A successful access to data in cache memory is known as hit. Normal 0 false false false EN-IN X-NONE X-NONE

Explain crossbar exchange, with all call processing steps and diagrams. The fundamental idea of crossbar switching is to give a matrix of n x m sets of contacts with only n + m

What is most common biometrics? Explain in brief. The most common biometrics is as given below: Face geometry (Photo): The computer captures the picture of your face and m

the c code for hypothetical reliable data transfer protocol

How optimization is achieved in DNS? Two primary optimizations used in DNS and they are: replication and caching. All root servers is replicated; various copies of the server

Write a program to mask bits D3D2D1D0 and to set bits D5D4 and to invert bits D7D6 of the AX register.