brain.js 神经网络的正确训练

Question

我肯定是误会了 brain.js instructions on training

我玩过这个 repl.it code

const brain = require('brain.js');

const network = new brain.NeuralNetwork();

network.train([
    { input: { doseA: 0 }, output: { indicatorA: 0 } },
    { input: { doseA: 0.1 }, output: { indicatorA: 0.02 } },
    { input: { doseA: 0.2 }, output: { indicatorA: 0.04 } },
    { input: { doseA: 0.3 }, output: { indicatorA: 0.06 } },
    { input: { doseA: 0.4 }, output: { indicatorA: 0.08 } },
    { input: { doseA: 0.5 }, output: { indicatorA: 0.10 } },
    { input: { doseA: 0.6 }, output: { indicatorA: 0.12 } },
    { input: { doseA: 0.7 }, output: { indicatorA: 0.14 } },
]);

const result = network.run({ doseA: 0.35 });

console.log(result);

>> { indicatorA: 0.12165333330631256 }
    => undefined

期望结果是 { indicatorA: 0.07 }

我做错了什么？

Answer 1

增加迭代次数和降低错误阈值对我有用：

const brain = require('brain.js');

const network = new brain.NeuralNetwork();

network.train([
    { input: { doseA: 0 }, output: { indicatorA: 0 } },
    { input: { doseA: 0.1 }, output: { indicatorA: 0.02 } },
    { input: { doseA: 0.2 }, output: { indicatorA: 0.04 } },
    { input: { doseA: 0.3 }, output: { indicatorA: 0.06 } },
    { input: { doseA: 0.4 }, output: { indicatorA: 0.08 } },
    { input: { doseA: 0.5 }, output: { indicatorA: 0.10 } },
    { input: { doseA: 0.6 }, output: { indicatorA: 0.12 } },
    { input: { doseA: 0.7 }, output: { indicatorA: 0.14 } },
], {
  log: true,
  iterations: 1e6,
  errorThresh: 0.00001
});

const result = network.run({ doseA: 0.35 });

console.log(result);
// 

结果：{ indicatorA: 0.0693388432264328 }