Brain.js in Machine Learning

Brain.js is a JavaScript library that makes it easy to understand artificial neural networks because it hides the complexity of the operations.

Building artificial neural networks

Building artificial neural networks with Brain.js:

 

For example:

// Create a Neural Network const network = new brain.NeuralNetwork(); // Train the Network with 4 input objects network.train([ {input:[0,0], output:{zero:1}}, {input:[0,1], output:{one:1}}, {input:[1,0], output:{one:1}, {input:[1,1], output:{zero:1}, ]); // What is the expected output of [1,0]? result = network.run([1,0]); // Display the probability for "zero" and "one" . result["one"] + " " + result["zero"];

Explain the example:

An artificial neural network is created using the command: `new brain.NeuralNetwork()`

 

The network was trained using the command `network.train([examples])`

The examples represent four input values ​​with their corresponding output values.

With the command `network.run([1,0])`, you are asking "What is the most likely output value of [1,0]?"

The answer from the internet is:

1. 1: 93% (almost 1)
2. 0: 6% (close to 0)

How to predict contrast

With CSS , colors can be set using RGB:

For example:

Màu	RGB
Đen	RGB(0,0,0)
Vàng	RGB(255,255,0)
Đỏ	RGB(255,0,0)
Trắng	RGB(255,255,255)
Xám nhạt	RGB(192,192,192)
Xám đậm	RGB(65,65,65)

The following example illustrates how to predict the intensity of a color:

For example:

// Create a Neural Network const net = new brain.NeuralNetwork(); // Train the Network with 4 input objects net.train([ // White RGB(255, 255, 255) {input:[255/255, 255/255, 255/255], output:{light:1}}, // Light grey (192,192,192) {input:[192/255, 192/255, 192/255], output:{light:1}}, // Darkgrey (64, 64, 64) { input:[65/255, 65/255, 65/255], output:{dark:1}}, // Black (0, 0, 0) { input:[0, 0, 0], output:{dark:1}}, ]); // What is the expected output of Dark Blue (0, 0, 128)? let result = net.run([0, 0, 128/255]); // Display the probability of "dark" and "light" . result["dark"] + " " + result["light"];

Explain the example:

An artificial neural network is created using the command: `new brain.NeuralNetwork()`

The network was trained using the command `network.train([examples])`

The examples represent four input values ​​and one corresponding output value.

With the command `network.run([0,0,128/255])`, you are asking "What is the most likely output value of dark blue?"

The answer from the internet is:

1. Dark: 95%
2. Mild: 4%

Why not modify the example to test the most likely output value of yellow or red?