Sigmoid units - Artificial intelligence

Remember that the function inside units take as input the weighted sum, S, of the values coming from the units associated to it. The function inside sigmoid units calculates the following value that given a real-valued input S:

Where e is the base of natural logarithms, e = 2.718...

When we plot the output from sigmoid units given several weighted sums as input, it seems remarkably like a step function:

 

Certainly, getting a differentiable function which seems like the step function was the main point of the exercise. Definitely, not only is this function differentiable, but the derivative is fairly expressed simply in terms of the function itself:

Notice that the output values for the σ function range between but never make it to 1and 0. This is because e-S is never -ve, and the denominator of the fraction tends to 0 as S gets very large  in the -ve direction, and tends to 1 as it gets very large in the +ve direction. This tendency happens quickly: the middle ground between 0 and 1 is hardly ever seen because of the sharp (near) step in the function. Because of it seems like a step function, we may think of it firing and not-firing as in a perceptron: if a positive real is input, the output will normally be close to +1 and if a negative real is input the output will normally be close to -1.

Posted Date: 10/2/2012 6:16:27 AM | Location : United States

Ask an Expert

Related Discussions:- Sigmoid units-artificial intelligence, Assignment Help, Ask Question on Sigmoid units-artificial intelligence, Get Answer, Expert's Help, Sigmoid units-artificial intelligence Discussions

Write discussion on Sigmoid units-artificial intelligence
Your posts are moderated

Write your message here..

Related Questions

Register data type as combinational element, Reg data type as Combinational... Reg data type as Combinational element module reg_combo_example( a, b, y); input a, b; output y; reg y; wire a, b; always @ ( a or b) begin y = a & b; e

Two different ways of building a match code object, What are the two differ... What are the two different ways of building a match code object? A match code can be built in two dissimilar ways: Logical structure: The matchcode data is set up not pe

The number of control lines for a 8 – to – 1 multiplexer, What is the numbe... What is the number of control lines for a 8 - to - 1 multiplexer ? Ans. There are 3 control lines, for an 8 to 1 Multiplexer. The control signals are utilized to steer any one

Assembly Language, Write an assembly program to simulate a microwave Write an assembly program to simulate a microwave

Communication of request/response - procedural interaction, Explain the Com... Explain the Communications of Request/Response Communications requirements for message or procedural- based interaction are very similar. Application interaction (client-server

Define both fork and vfork, How and when race conditions happen in process ... How and when race conditions happen in process control? How can it be avoided? b. Differentiate among following functions giving related syntax: (i) fork and vfork (ii) w

Define about hyper-threading technology, Q. Define about Hyper-threading te... Q. Define about Hyper-threading technology? Hyper-threading technology enables a single microprocessor to behave as two separate threaded processors to operating system and app

Operating sustem, describe the action by thread library to context switch ... describe the action by thread library to context switch between user level threads

Implementation of 4-to-1 multiplexer, Implement the Y(A, B, C) = ∑(2,3,5,6)... Implement the Y(A, B, C) = ∑(2,3,5,6) function using 4-to-1 multiplexer.   Ans. Y(A,B,C)=∑(2,3,5,6) Here we take B,C as the select bits also A as input. To select the input we can

Digital communication, define multipoint communication define multipoint communication