突触js lstm rnn算法的死简单例子 [英] Dead simple example of synaptic js lstm rnn algorithm

问题描述

LSTM RNN预测时间序列数据的死简单示例非常疯狂。

It's pretty crazy that there isn't a dead simple example of the LSTM RNN predicting time series data.

https://github.com/cazala/synaptic

https://github.com/cazala/synaptic/wiki/Architect#lstm

我想使用以下数组中的历史数据：

I'd like to use the historical data in the following array:

const array = [
    0,
    0,
    0,
    1,
    0,
    0,
    0,
    1
];

一些漂亮的心灵数据就在那里吗？

Some pretty mind blowing data right there right?

我想A）使用数组训练算法然后B）使用以下数组测试算法：

I'd like to A) train the algorithm with the array then B) test the algorithm with the following array:

const array = [
    0,
    0,
    0,
    1,
    0,
    0,
    0,
    1,
    0
];

应该导致它预测 0 。

不幸的是文档非常糟糕，没有明确的代码示例。有人有任何例子吗？

Unfortunately the documentation is pretty bad, no clear code examples exist. Anyone have any examples?

推荐答案

这个答案不是用Synaptic写的，而是用 Neataptic 。我决定快速回答一下，我将很快将其纳入文档中。这是代码，它工作9/10次：

This answer is not written with Synaptic, but with Neataptic. I decided to make a quick answer that I will include in the documentation soon. This is the code, it works 9/10 times:

var network = new neataptic.architect.LSTM(1,6,1);

// when the timeseries is [0,0,0,1,0,0,0,1...]
var trainingData = [
  { input: [0], output: [0] },
  { input: [0], output: [0] },
  { input: [0], output: [1] },
  { input: [1], output: [0] },
  { input: [0], output: [0] },
  { input: [0], output: [0] },
  { input: [0], output: [1] },
];

network.train(trainingData, {
  log: 500,
  iterations: 6000,
  error: 0.03,
  clear: true,
  rate: 0.05,
});

在JSFIDDLE上运行它以查看预测！要获得更多预测，请打开这一个。

Run it on JSFIDDLE to see the prediction! For more predictions, open this one.

我做出的一些选择的解释：

Explanation to some choices I made:

• 我设定选项清除为true，因为您需要按时间顺序进行时间序列预测。这可确保网络从每次训练迭代的开始开始，而不是从最后一次迭代的结束继续。


• 费率相当低，将获得更高的费率卡在MSE错误 ~0.2


• LSTM有1块6个内存节点，较低的数量似乎不起作用还有。

• I set option clear to true, as you want do a chronological timeseries prediction. This makes sure that the network starts from the 'beginning' every training iteration, instead of continuing on from the 'end' of the last iteration.
• Rate is fairly low, higher rates will get stuck at an MSE error of ~0.2
• The LSTM has 1 block of 6 memory nodes, lower amounts don't seem to work as well.

这篇关于突触js lstm rnn算法的死简单例子的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！