Going by the preceding table, the network is trying to find a relationship between input and output. For example, let's assume the relationship that comes through is the following:
Y = W. X
In the preceding equation, Y and X are known, and based on that W has to be found out. But, finding out the value of W in one iteration is rare. It has to be initialized first. Let's say W is initialized with the value of 3. And the equation turns out to be as follows:
Y= 3X
| Input (X) | Actual Output (Y) |
| 2 | 6 |
| 3 | 9 |
| 4 | 12 |
| 5 | 15 |
| 6 | 18 |
Now we have to assess the output and whether it is close to the desired output.