how to make pseudocode of perceptron in python?

Question

This code was written in python 3, could you tell me what your pseudocode would look like? I can not understand the calculations that are being made:

#dobro n * 2
# x * weight

import random
import numpy as np

   def derivada(n):
        return n*(1-n)

x = 0.85 
y = 0.25
w = random.random()

#épocas

for i in range(10):
     a=np.tanh(x*w)

     e = y-a#erro

     w+= x* derivada(e)

     print(a)

I tried to do the pseudocode this way, but it's not working too well.

     algoritm "untitled"

            var
                er, n, f, x1, w1, w2, u, y : real
                                  b, yd, i : inteiro
           Begin
               b <- 1
               x1 <- 1
               w1 <- 0
               u <- (x1*w1)+b
               y <- tan(u)
               yd <- 5
               er <- yd-y
               for i de 1 to 10 do
               n <- 0.5
               f <- (n*x1*er)
               w1 <- w1+f
               Write(w1)
               endfor

               // Commands
          End

Can you tell me what's wrong?

Answer 1

Basically, what's happening is you have these variables:

x - Input value to perceptron

y - Expected output from perceptron

w - Weight value on perceptron

The derivato(n) function returns the derivative of the tanh curve. This is used to calculate the adjustment to the w variable.

x is set to 0.85, y is set to 0.25. w is initialized to a random number.

10 times, a is the output of the perceptron. This is equal to tanh(x*w) where x is the input, w is the weight, and tanh being the tanh function.

The error ( e variable) is calculated by doing ya , where y is the expected output. (the ground truth)

The adjustment to the weight ( w ) is calculated by calculating the derivative of the tanh curve at e and multiplying by x . So the adjustment is x*derivato(e)

Then, the adjustment is added to the weight, to adjust it.