blocks|key|2581935|text|假设您已经为BP使用了一些库，那么使用BP作为流程中的一个步骤来实现BPTT应该是相当简单的。|type|unstyled|depth|inlineStyleRanges|entityRanges|data|2581936|BPTT+1的维基百科条目包括相关的伪代码。|2581937|我自己的出发点，大约是18年前，是“卡车杀手-上部:神经网络中自我学习的一个例子”2。|2581938|1|offset|length|2581939|2|2581940|entityMap|0|LINK|mutability|MUTABLE|url|http://en.wikipedia.org/wiki/Backpropagation_through_time|http://www-isl.stanford.edu/~widrow/papers/c1989thetruck.pdf^0|0|0|0|0|1|0|0|0|1|1|0^^$0|@$1|2|3|4|5|6|7|U|8|@]|9|@]|A|$]]|$1|B|3|C|5|6|7|V|8|@]|9|@]|A|$]]|$1|D|3|E|5|6|7|W|8|@]|9|@]|A|$]]|$1|F|3|G|5|6|7|X|8|@]|9|@$H|Y|I|Z|1|10]]|A|$]]|$1|J|3|K|5|6|7|11|8|@]|9|@$H|12|I|13|1|14]]|A|$]]|$1|L|3|-4|5|6|7|15|8|@]|9|@]|A|$]]]|M|$N|$5|O|P|Q|A|$R|S]]|G|$5|O|P|Q|A|$R|T]]]]

Assuming you're already using some library for BP, it should be (TM) rather straightforward to implement BPTT using BP as a step in the process.

The Wikipedia entry for BPTT [1] includes relevant pseudo code. 

My own starting point, about 18 years ago, was "The Truck Backer-Upper: An Example of Self-Learning in Neural Networks" [2].

[1] <a href="http://en.wikipedia.org/wiki/Backpropagation_through_time" rel="nofollow">http://en.wikipedia.org/wiki/Backpropagation_through_time</a>

[2] <a href="http://www-isl.stanford.edu/~widrow/papers/c1989thetruck.pdf" rel="nofollow">http://www-isl.stanford.edu/~widrow/papers/c1989thetruck.pdf</a>

blocks|key|2298632|text|不过，我使用NeuronDotNet的时间有限。它允许您创建前馈BackPropagation神经网络。我特别喜欢他们使用直观命名的类。祝好运!|type|unstyled|depth|inlineStyleRanges|entityRanges|offset|length|data|2298633|这是一个.net库。|2298634|entityMap|0|LINK|mutability|MUTABLE|url|http://neurondotnet.freehostia.com/manual/index.html^0|6|C|0|0|0^^$0|@$1|2|3|4|5|6|7|N|8|@]|9|@$A|O|B|P|1|Q]]|C|$]]|$1|D|3|E|5|6|7|R|8|@]|9|@]|C|$]]|$1|F|3|-4|5|6|7|S|8|@]|9|@]|C|$]]]|G|$H|$5|I|J|K|C|$L|M]]]]

I've used <a href="http://neurondotnet.freehostia.com/manual/index.html" rel="nofollow noreferrer">NeuronDotNet</a> only for a limited time though. It allows you to create a feed-forward BackPropagation NN. I especially liked their use of intuitively named classes. Good luck!
This is a .net library.

blocks|key|4373522|text|也许pybrain会怎么样呢？它的BackpropTrainer类的文档字符串表明它在时间上进行反向传播：|type|unstyled|depth|inlineStyleRanges|offset|length|style|CODE|entityRanges|data|4373523|class+BackpropTrainer(Trainer):
++++"""Trainer+that+trains+the+parameters+of+a+module+according+to+a
++++supervised+dataset+(potentially+sequential)+by+backpropagating+the+errors
++++(through+time)."""|code-block|syntax|javascript|4373524|entityMap|0|LINK|mutability|MUTABLE|url|http://pybrain.org/^0|H|F|2|7|0|0|0^^$0|@$1|2|3|4|5|6|7|S|8|@$9|T|A|U|B|C]]|D|@$9|V|A|W|1|X]]|E|$]]|$1|F|3|G|5|H|7|Y|8|@]|D|@]|E|$I|J]]|$1|K|3|-4|5|6|7|Z|8|@]|D|@]|E|$]]]|L|$M|$5|N|O|P|E|$Q|R]]]]

Perhaps <a href="http://pybrain.org/" rel="nofollow">pybrain</a> would do? The docstring for its <code>BackpropTrainer</code> class suggests that it does backpropagation through time:

<pre><code>class BackpropTrainer(Trainer):
 """Trainer that trains the parameters of a module according to a
 supervised dataset (potentially sequential) by backpropagating the errors
 (through time)."""
</code></pre>

blocks|key|679550|text|那this+one呢？只是在谷歌上搜索一下就行了。|type|unstyled|depth|inlineStyleRanges|entityRanges|offset|length|data|679551|entityMap|0|LINK|mutability|MUTABLE|url|http://snarli.sourceforge.net/docs/edu/wlu/cs/levy/SNARLI/BPLayer.html^0|1|8|0|0^^$0|@$1|2|3|4|5|6|7|L|8|@]|9|@$A|M|B|N|1|O]]|C|$]]|$1|D|3|-4|5|6|7|P|8|@]|9|@]|C|$]]]|E|$F|$5|G|H|I|C|$J|K]]]]

What about <a href="http://snarli.sourceforge.net/docs/edu/wlu/cs/levy/SNARLI/BPLayer.html" rel="nofollow">this one</a> ? Just a Google search to help...

blocks|key|2582598|text|我有Java背景，但Encog也有一个.net实现(这是一个非常好的NNets框架，有很好的时间序列支持)|type|unstyled|depth|inlineStyleRanges|entityRanges|offset|length|data|2582599|我对F#框架无能为力，但是你在为哪个领域编码呢？如果是金融，我会重申“看一看Encog”|2582600|entityMap|0|LINK|mutability|MUTABLE|url|http://www.heatonresearch.com/encog^0|A|5|0|0|0^^$0|@$1|2|3|4|5|6|7|N|8|@]|9|@$A|O|B|P|1|Q]]|C|$]]|$1|D|3|E|5|6|7|R|8|@]|9|@]|C|$]]|$1|F|3|-4|5|6|7|S|8|@]|9|@]|C|$]]]|G|$H|$5|I|J|K|C|$L|M]]]]

I'm from a Java background but <a href="http://www.heatonresearch.com/encog" rel="nofollow">Encog</a> has a .net implementation as well (and is a seriously good framework for NNets, with good time series support)

Can't help with an F# framework, but what domain are you coding for? If it's finance I'll reassert the "take a look at Encog"

blocks|key|4373687|text|我对Weka有很好的体验-在我看来，它是最好的，也是几乎可以肯定是最全面的通用机器学习库之一。|type|unstyled|depth|inlineStyleRanges|entityRanges|offset|length|data|4373688|你当然可以用Weka做BPTT+-你可能会找到一个现成的分类器来做你需要的事情，但即使不是这样，你也可以按照非常好的wikipedia+article+on+BPTT将几个普通的反向传播单元链接在一起。|4373689|entityMap|0|LINK|mutability|MUTABLE|url|http://www.cs.waikato.ac.nz/ml/weka/|1|http://en.wikipedia.org/wiki/Backpropagation_through_time^0|2|4|0|0|1M|P|1|0^^$0|@$1|2|3|4|5|6|7|P|8|@]|9|@$A|Q|B|R|1|S]]|C|$]]|$1|D|3|E|5|6|7|T|8|@]|9|@$A|U|B|V|1|W]]|C|$]]|$1|F|3|-4|5|6|7|X|8|@]|9|@]|C|$]]]|G|$H|$5|I|J|K|C|$L|M]]|N|$5|I|J|K|C|$L|O]]]]

I've had good experiences with <a href="http://www.cs.waikato.ac.nz/ml/weka/" rel="nofollow">Weka</a> - In my view one of the best and almost certainly the most comprehensive general purpose machine learning libraries around. 

You could certainly do BPTT with Weka - you may find a ready made classifier that does what you need but even if not you can just chain a few normal backpropagation units together as per the very good <a href="http://en.wikipedia.org/wiki/Backpropagation_through_time" rel="nofollow">wikipedia article on BPTT</a>

blocks|key|2582733|text|我很久以前就用Java做了反向传播算法。我已经把它上传到GitHub了，也许你会发现它很有用：https://github.com/bernii/NeuralNetwokPerceptronKohonen|type|unstyled|depth|inlineStyleRanges|entityRanges|offset|length|data|2582734|现在让我看看它是否对您有帮助:)|2582735|entityMap|0|LINK|mutability|MUTABLE|url|https://github.com/bernii/NeuralNetwokPerceptronKohonen^0|1B|1J|0|0|0^^$0|@$1|2|3|4|5|6|7|N|8|@]|9|@$A|O|B|P|1|Q]]|C|$]]|$1|D|3|E|5|6|7|R|8|@]|9|@]|C|$]]|$1|F|3|-4|5|6|7|S|8|@]|9|@]|C|$]]]|G|$H|$5|I|J|K|C|$L|M]]]]

I made backpropagation algorithm in Java quite time ago. I uploaded it into GitHub, maybe you can find it useful: <a href="https://github.com/bernii/NeuralNetwokPerceptronKohonen" rel="nofollow">https://github.com/bernii/NeuralNetwokPerceptronKohonen</a>

Let me now if it was helpful :)

blocks|key|2582778|text|你可以使用TensorFlow的dynamic_rnn()函数(API+doc)，TensorFlow的tutorial+on+Recurrent+Neural+Networks将会有所帮助。|type|unstyled|depth|inlineStyleRanges|offset|length|style|CODE|entityRanges|data|2582779|此外，这个很棒的blog+post为使用TensorFlow预测序列提供了一个很好的介绍。这是另一个使用some+code预测时间序列的blog+post。|2582780|entityMap|0|LINK|mutability|MUTABLE|url|http://tensorflow.org/|1|https://www.tensorflow.org/versions/r0.10/api_docs/python/nn.html#dynamic_rnn|2|https://www.tensorflow.org/versions/r0.10/tutorials/recurrent/index.html|3|https://danijar.com/introduction-to-recurrent-networks-in-tensorflow/|4|https://github.com/mouradmourafiq/tensorflow-lstm-regression/blob/master/lstm.py|5|http://mourafiq.com/2016/05/15/predicting-sequences-using-rnn-in-tensorflow.html^0|G|D|5|A|0|W|7|1|1G|11|2|0|8|9|3|1G|9|4|1W|9|5|0^^$0|@$1|2|3|4|5|6|7|Z|8|@$9|10|A|11|B|C]]|D|@$9|12|A|13|1|14]|$9|15|A|16|1|17]|$9|18|A|19|1|1A]]|E|$]]|$1|F|3|G|5|6|7|1B|8|@]|D|@$9|1C|A|1D|1|1E]|$9|1F|A|1G|1|1H]|$9|1I|A|1J|1|1K]]|E|$]]|$1|H|3|-4|5|6|7|1L|8|@]|D|@]|E|$]]]|I|$J|$5|K|L|M|E|$N|O]]|P|$5|K|L|M|E|$N|Q]]|R|$5|K|L|M|E|$N|S]]|T|$5|K|L|M|E|$N|U]]|V|$5|K|L|M|E|$N|W]]|X|$5|K|L|M|E|$N|Y]]]]

You can use <a href="http://tensorflow.org" rel="nofollow">TensorFlow</a>'s <code>dynamic_rnn()</code> function (<a href="https://www.tensorflow.org/versions/r0.10/api_docs/python/nn.html#dynamic_rnn" rel="nofollow">API doc</a>). TensorFlow's <a href="https://www.tensorflow.org/versions/r0.10/tutorials/recurrent/index.html" rel="nofollow">tutorial on Recurrent Neural Networks</a> will help.

Also, this great <a href="https://danijar.com/introduction-to-recurrent-networks-in-tensorflow/" rel="nofollow">blog post</a> provides a nice introduction to predicting sequences using TensorFlow. Here's another <a href="http://mourafiq.com/2016/05/15/predicting-sequences-using-rnn-in-tensorflow.html" rel="nofollow">blog post</a> with <a href="https://github.com/mouradmourafiq/tensorflow-lstm-regression/blob/master/lstm.py" rel="nofollow">some code</a> to predict a time series.

Does anyone know of a library with a working implementation of backpropagation through time?
Any of Java/Python/C#/VB.NET/F# (preferably the last one) will do!

Backpropagation through time

翻译质量差，导致语言生硬或混乱。

没有提供实际的解决方法或示例。

解答不清晰，无法理解或解决问题。

页面排版不美观，阅读体验差。

文章

问答

视频

学习中心

腾讯云实验室

直播

竞赛

腾讯云代码分析专区

腾讯iOA零信任安全管理系统专区

腾讯云架构师技术同盟交流圈

腾讯云数据库专区

腾讯云顾问专区

腾讯云原生专区

腾讯混元专区

腾讯云TCE专区

腾讯云Lighthouse专区

腾讯云HAI专区

腾讯云Edgeone专区

腾讯云存储专区

腾讯云智能专区

腾讯轻联专区 

腾讯云开发专区

TAPD专区

腾讯轻量云游戏服专区

腾讯云最具价值专家

腾讯云架构师技术同盟

腾讯云创作之星

腾讯云开发者先锋

腾讯云代码助手

云原生构建

TAPD 敏捷项目管理

Cloud Studio

SDK中心

API中心

命令行工具

涵盖代码开发、场景应用、自动测试全流程，助你从零构建专属AI助手

一站式MCP教程库，解锁AI应用新玩法

有没有人知道有一个可以通过时间反向传播的库？Java/Python/C#/VB.NET/F#中的任何一个(最好是最后一个)都可以！

问时间反向传播
EN

Stack Overflow用户

社区

活动

圈层

关于

腾讯云开发者

热门产品

热门推荐

更多推荐

问时间反向传播EN