Great! Now that you understand the structure of the perceptron, here’s an important question — how are the inputs and weights magically turned into an output? This is a two-step process, and the first step is finding the weighted sum of the inputs.
What is the weighted sum? This is just a number that gives a reasonable representation of the inputs:
The x‘s are the inputs and the w‘s are the weights.
Here’s how we can implement it:
- Start with a weighted sum of 0. Let’s call it
weighted_sum
. - Start with the first input and multiply it by its corresponding weight. Add this result to
weighted_sum
. - Go to the next input and multiply it by its corresponding weight. Add this result to
weighted_sum
. - Repeat this process for all inputs.
Instructions
Create a variable called weighted_sum
to hold the value of the weighted sum and set its starting value to 0
.
Return weighted_sum
outside the for
loop.
Let’s go through each input-weight pair and find the weighted sum using indexing.
Delete the pass
statement inside the for
loop. For each iteration in the loop, find the product of the input and weight at index i
, add the result to weighted_sum
, and store it back in weighted_sum
to update the value of weighted_sum
.
Outside the Perceptron
class, after the Perceptron
object cool_perceptron
has been created, print out the weighted sum for the inputs [24, 55]
.
What is the weighted sum?