Brain.js
Brain.js — matematikaning murakkabligini yashirgani sababli neyron tarmoqlarni tushunishni osonlashtiradigan JavaScript kutubxonasi.
Neyron tarmoq qurish
Brain.js yordamida neyron tarmoq qurish:
Misol:
// 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"];
O‘zingiz sinab ko‘ring »
Misol izohi:
Neyron tarmoq quyidagicha yaratiladi: new brain.NeuralNetwork()
Tarmoq network.train([examples]) yordamida o‘qitiladi
Misollar 4 ta kirish qiymatini va ularga mos chiqish qiymatlarini ifodalaydi.
network.run([1,0]) orqali siz "[1,0] uchun ehtimoliy natija qanday?" deb so‘raysiz.
Tarmoqning javobi:
- one: 93% (1 ga yaqin)
- zero: 6% (0 ga yaqin)
Kontrastni qanday bashorat qilish mumkin
CSS’da ranglarni RGB orqali belgilash mumkin:
Misol
| Color | RGB |
|---|---|
| Black | RGB(0,0,0) |
| Yellow | RGB(255,255,0) |
| Red | RGB(255,0,0) |
| White | RGB(255,255,255) |
| Light Gray | RGB(192,192,192) |
| Dark Gray | RGB(65,65,65) |
Quyidagi misol rangning qanchalik to‘qligini bashorat qilishni namoyish etadi:
Misol:
// 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"];
O‘zingiz sinab ko‘ring »
Misol izohi:
Neyron tarmoq quyidagicha yaratiladi: new brain.NeuralNetwork()
Tarmoq network.train([examples]) yordamida o‘qitiladi
Misollar 4 ta kirish qiymatini va ularga mos chiqish qiymatlarini ifodalaydi.
network.run([0,0,128/255]) orqali siz "to‘q ko‘k rang uchun ehtimoliy natija qanday?" deb so‘raysiz.
Tarmoqning javobi:
- Dark: 95%
- Light: 4%
Nega misolni tahrirlab, sariq yoki qizil rang uchun ehtimoliy natijani sinab ko‘rmaysiz?
W3Schools Pathfinder
Yutuqlaringizni kuzating – bu bepul!