APPLICATION OF SUPERVISED LEARNING
NEURAL NETWORK
|
Question
[CLICK ON ANY CHOICE TO KNOW THE RIGHT ANSWER]
|
A 4-input neuron has weights 1, 2, 3 and 4. The activation function is linear with the constant of proportionality being equal to 2 (y=2x). The inputs, Ox are 4, 10, 5 and 20 respectively. What will be the output, Oy?
|
|
238
|
|
|
76
|
|
|
119
|
|
|
123
|
Explanation:
Detailed explanation-1: -Ans : BExplanation: The output is found by multiplying the weights with their respective inputs, summing the results and multiplying with the transfer function. Therefore: Output = 2 * (1*4+ 2*3 + 3*2 + 4*1) = 40.
Detailed explanation-2: -A 4-input neuron has weights 1, 2, 3 and 4. The transfer function is linear with the constant of proportionality being equal to 2.
Detailed explanation-3: -If you are using a sigmoid function, its output will be 0.5 when its input is zero.
Detailed explanation-4: -Initializing all the weights with zeros leads the neurons to learn the same features during training. In fact, any constant initialization scheme will perform very poorly.
There is 1 question to complete.