2 Neuron Model and Network Architectures Given a two-input neuron with the follo

Question

2 Neuron Model and Network Architectures Given a two-input neuron with the following weight matrix and input vector: W = [3 -2] and p = [-7 7]^T, we would like to have an output of 0.5. Do you suppose that there is a combination of bias and transfer function that might allow this? Is there a transfer function from Table 2.1 that will do the job if the bias is zero? Is there a bias that will do the job if the linear transfer function is used? If yes, what is it? Is there a bias that will do the job if a log-sigmoid transfer function is used? Again, if yes, what is it? Is there a bias that will do the job if a symmetrical hard limit transfer function is used? Again, if yes, what is it?

Explanation / Answer

A - since bias is zero, a=f(n) where n is W*P=-25, so there is no transfer function which can give output 25.

B - Yes, since output is equal to input take bias as 25.5 so n=W*P+bias, and as W*P is -25, n=0.5 which is output

C - Yes as we need output as 0.5 we need n to be zero which can happen if bias is 25, so 25-25=0 and we get output as 0.5

D - No as the only possible output when symmetric hard limit is used is 1 and -1, so it is not possible.

Related Questions

Navigate

• Browse (All)
• Browse 2
• Subjects

---

---

Integrity-first tutoring: explanations and feedback only — we do not complete graded work. Learn more.