Medium article: https://medium.com/@waywardverities/making-a-perceptron-in-javascript-because-its-inefficient-a16ea21ce02c
const X_inputs = [
[0, 0],
[0, 1],
[1, 0],
[1, 1]
]
const y_outputs = [
0,
1,
1,
1
]
// Settings
const epochs = 5
const learning_rate = 0.01
const log_epochs = false
let weights = [0, 0]
let bias = 0
for (i = 0; i < epochs; i++) {
if (log_epochs) console.log(`⏩ Epoch ${i}`)
// Loop through each in/output every epoch
for (j = 0; j < y_outputs.length; j++) {
x = X_inputs[j]
y_target = y_outputs[j]
// Prediction can only be 0 or 1, error can be -1, 0 or 1
y_predicted = predict(x)
error = y_target - y_predicted
if (log_epochs) console.log(`${x} ⏩ Target y: ${y_target} ⏩ Predicted y: ${y_predicted} / error: ${error}`)
// Update the weights and the bias
weights = weights.map((weight, i) => {
return weight += x[i] * error * learning_rate
})
bias += learning_rate * error
if (log_epochs) console.log(`Weights ${weights} / bias ${bias}`)
}
if (log_epochs) console.log(`After epoch: ${weights} - ${bias}`)
}
console.log(`Bias after ${bias}`)
console.log(`Weights after ${weights}`)
// Uses global weights and bias
function predict(x) {
const y_pred = x[0] * weights[0] + x[1] * weights[1] + bias
if (y_pred >= 0) {
return 1
} else {
return 0
}
}
console.log({weights, bias})
console.log([0,0], predict([0,0]))
console.log([0,1], predict([0,1]))
console.log([1,0], predict([1,0]))
console.log([1,1], predict([1,1]))
no comments
sign in to comment