mempirate

# Train by iterating 10,000 times
for iteration in range(10000):
  
  # Define input layer
  input_layer = training_inputs
  
  # Normalize the product of the input layer with the synaptic 
  # weights by using the sigmoid function to get outputs
  outputs = sigmoid(np.dot(input_layer, synaptic_weights))
  

mempirate

# Set seed for pseudo-randomness
np.random.seed(1)

# Initialize synaptic weights randomly from -1 to 1 with 0 as the mean
synaptic_weights = 2 * np.random.random((3, 1)) - 1

mempirate

# Input matrix
training_inputs = np.array([[0,0,1],
                            [1,1,1],
                            [1,0,1],
                            [0,1,1]])
# Output array (transposed)
training_outputs = np.array([[0,1,1,0]]).T

mempirate

import numpy as np

def sigmoid(x):
  return 1 / (1 + np.exp(-x))

def sigmoid_derivative(x):
  return x * (x - 1)

mempirate

Verifying my Blockstack ID is secured with the address 1Jzq7PkwGH34a6iF1PAL6QVuQqatY6MxZy https://explorer.blockstack.org/address/1Jzq7PkwGH34a6iF1PAL6QVuQqatY6MxZy