1. Home

Testing a Perceptron

Generate new unknown points and check if your Perceptron can guess the right answers

Test Your Library

Generate new unknown points and check if your Perceptron can guess the right answers:

Example

// Test Against Unknown Data
const counter = 500;
for (let i = 0; i < counter; i++) {
  let x = Math.random() * xMax;
  let y = Math.random() * yMax;
  let guess = ptron.activate([x, y, ptron.bias]);
  let color = "black";
  if (guess == 0) color = "blue";
  plotter.plotPoint(x, y, color);
}

Try it Yourself »

Count the Errors

Add a counter to count the number of errors:

Example

// Test Against Unknown Data
const counter = 500;
let errors = 0;
for (let i = 0; i < counter; i++) {
  let x = Math.random() * xMax;
  let y = Math.random() * yMax;
  let guess = ptron.activate([x, y, ptron.bias]);
  let color = "black";
  if (guess == 0) color = "blue";
  plotter.plotPoint(x, y, color);
  if (y > f(x) &amp; guess == 0) {errors++}
}

Try it Yourself »

Tune the Perceptron

How can you tune the Perceptron?

Here are some suggestions:

  • Adjust the learning rate
  • Increase the number of training data
  • Increase the number of training iterations

    • Categories

    HTML CSS3 Bootstrap Foundation Sass JavaScript TypeScript JQuery AngularJS React NodeJS Highcharts PHP Python Python3 Django Linux Docker Ruby Java C C ++ Perl Servlet JSP Lua Scala Go ASP C # SQL MySQL SQLite MongoDB Redis Android Swift ionic Kotlin XML tutorial

    Contact US