blocks|key|1402084|text|我不完全确定，但我会说，使用最大数量的输入(例如，对于单词，假设单词不会超过45个字符(根据维基百科在字典中可以找到最长的单词)，如果遇到较短的单词，则将其他输入设置为空格字符。|type|unstyled|depth|inlineStyleRanges|entityRanges|data|1402085|或者对于二进制数据，将其设置为0。这种方法的唯一问题是，如果用空白字符/零/其他字符填充的输入与有效的全长输入冲突(与其说是单词的问题，不如说是数字的问题)。|1402086|entityMap^0|0|0^^$0|@$1|2|3|4|5|6|7|F|8|@]|9|@]|A|$]]|$1|B|3|C|5|6|7|G|8|@]|9|@]|A|$]]|$1|D|3|-4|5|6|7|H|8|@]|9|@]|A|$]]]|E|$]]

i'm not entirely sure, but I'd say, use the maximum number of inputs (e.g. for words, lets say no word will be longer than 45 characters (longest word found in a dictionary according to wikipedia), and if a shorter word is encountered, set the other inputs to a whitespace character.

Or with binary data, set it to 0. the only problem with this approach is if an input filled with whitespace characters/zeros/whatever collides with a valid full length input (not so much a problem with words as it is with numbers).

blocks|key|1402133|text|您通常会从数据中提取特征，并将这些特征提供给网络。仅仅获取一些数据并将其提供给网络是不可取的。在实践中，预处理和选择正确的特征将决定您的成功和神经网络的性能。不幸的是，我认为这需要经验来培养一种感觉，这不是一个人可以从一本书中学到的。|type|unstyled|depth|inlineStyleRanges|entityRanges|data|1402134|总结：“垃圾输入，垃圾输出”|1402135|entityMap^0|0|0^^$0|@$1|2|3|4|5|6|7|F|8|@]|9|@]|A|$]]|$1|B|3|C|5|6|7|G|8|@]|9|@]|A|$]]|$1|D|3|-4|5|6|7|H|8|@]|9|@]|A|$]]]|E|$]]

You would usually extract features from the data and feed those to the network. It is not advisable to take just some data and feed it to net. In practice, pre-processing and choosing the right features will decide over your success and the performance of the neural net. Unfortunately, IMHO it takes experience to develop a sense for that and it's nothing one can learn from a book.

Summing up: "Garbage in, garbage out"

blocks|key|1402188|text|有些问题可以用递归神经网络来解决。例如，它适用于计算输入序列的奇偶校验。|type|unstyled|depth|inlineStyleRanges|entityRanges|data|1402189|recurrent+neural+network+for+calculating+parity将只有一个输入特性。随着时间的推移，这些比特可以输入到其中。它的输出也被反馈到隐藏层。这使得只需要两个隐藏单元就可以学习奇偶校验。|offset|length|1402190|正常的前馈两层神经网络需要2**sequence_length隐藏单元来表示奇偶校验。这种limitation+holds适用于任何只有2层的架构(例如，支持向量机)。|1402191|entityMap|0|LINK|mutability|MUTABLE|url|http://github.com/pybrain/pybrain/blob/master/examples/supervised/backprop/parityrnn.py|1|http://yann.lecun.com/exdb/publis/pdf/bengio-lecun-07.pdf^0|0|0|1B|0|0|19|G|1|0^^$0|@$1|2|3|4|5|6|7|R|8|@]|9|@]|A|$]]|$1|B|3|C|5|6|7|S|8|@]|9|@$D|T|E|U|1|V]]|A|$]]|$1|F|3|G|5|6|7|W|8|@]|9|@$D|X|E|Y|1|Z]]|A|$]]|$1|H|3|-4|5|6|7|10|8|@]|9|@]|A|$]]]|I|$J|$5|K|L|M|A|$N|O]]|P|$5|K|L|M|A|$N|Q]]]]

Some problems could be solved by a recurrent neural network.
For example, it is good for calculating parity over a sequence of inputs.

The <a href="http://github.com/pybrain/pybrain/blob/master/examples/supervised/backprop/parityrnn.py" rel="noreferrer">recurrent neural network for calculating parity</a> would have just one input feature.
The bits could be fed into it over time. Its output is also fed back to the hidden layer.
That allows to learn the parity with just two hidden units.

A normal feed-forward two-layer neural network would require 2**sequence_length hidden units to represent the parity. This <a href="http://yann.lecun.com/exdb/publis/pdf/bengio-lecun-07.pdf" rel="noreferrer">limitation holds</a> for any architecture with just 2 layers (e.g., SVM).

blocks|key|1402259|text|我猜一种方法是在输入(递归神经网络)中添加一个时间成分，然后一次将输入流到网络中(基本上创建了相当于词法分析器和解析器的神经网络)这将允许输入相当大，但缺点是不一定有停止符号来分隔不同的输入序列(相当于句子中的句号)。|type|unstyled|depth|inlineStyleRanges|entityRanges|data|1402260|entityMap^0|0^^$0|@$1|2|3|4|5|6|7|D|8|@]|9|@]|A|$]]|$1|B|3|-4|5|6|7|E|8|@]|9|@]|A|$]]]|C|$]]

I guess one way to do it is to add a temporal component to the input (recurrent neural net) and stream the input to the net a chunk at a time (basically creating the neural network equivalent of a lexer and parser) this would allow the input to be quite large but would have the disadvantage that there would not necessarily be a stop symbol to seperate different sequences of input from each other (the equivalent of a period in sentances)

blocks|key|1186978|text|我去过那里，我遇到了这个问题。ANN是针对固定的特征向量长度进行的，KNN、SVM、贝叶斯等许多其他分类器也是如此，即输入层应该定义良好且不变，这是一个设计问题。然而，一些研究人员选择添加零来填补缺失的空白，我个人认为这不是一个好的解决方案，因为这些零(不真实的值)会影响网络将收敛到的权重。此外，可能会有一个以零结尾的真实信号。|type|unstyled|depth|inlineStyleRanges|entityRanges|data|1186979|ANN不是唯一的分类器，还有更多更好的分类器，比如随机森林。这个分类器被认为是研究人员中最好的，它使用少量的随机特征，使用自举和打包创建数百棵决策树，这可能工作得很好，所选特征的数量通常是特征向量大小的sqrt。这些特性是随机的。每个决策树都收敛到一个解决方案，使用多数规则，然后选择最可能的类。|1186980|另一种解决方案是使用动态时间规整DTW，或者更好地使用隐马尔可夫模型HMM。|1186981|另一种解决方案是内插，内插(补偿沿小信号的缺失值)所有小信号具有与最大信号相同的大小，内插方法包括但不限于平均，B样条，立方.|1186982|另一种解决方案是使用特征提取方法，利用最好的(最有特色的)特征，这次使它们的大小固定，这些方法包括PCA，LDA等。|1186983|另一种解决方案是使用特征选择(通常在特征提取之后)，这是一种简单的方法，可以选择提供最佳精度的最佳特征。|1186984|这就是目前的全部，如果这些都不适用于你，请与我联系。|1186985|entityMap^0|0|0|0|0|0|0|0^^$0|@$1|2|3|4|5|6|7|P|8|@]|9|@]|A|$]]|$1|B|3|C|5|6|7|Q|8|@]|9|@]|A|$]]|$1|D|3|E|5|6|7|R|8|@]|9|@]|A|$]]|$1|F|3|G|5|6|7|S|8|@]|9|@]|A|$]]|$1|H|3|I|5|6|7|T|8|@]|9|@]|A|$]]|$1|J|3|K|5|6|7|U|8|@]|9|@]|A|$]]|$1|L|3|M|5|6|7|V|8|@]|9|@]|A|$]]|$1|N|3|-4|5|6|7|W|8|@]|9|@]|A|$]]]|O|$]]

I have been there, and I faced this problem.
The ANN was made for fixed feature vector length, and so are many other classifiers such as KNN, SVM, Bayesian, etc. 
 i.e. the input layer should be well defined and not varied, this is a design problem.
However, some researchers opt for adding zeros to fill the missing gap, I personally think that this is not a good solution because those zeros (unreal values) will affect the weights that the net will converge to. in addition there might be a real signal ending with zeros. 

ANN is not the only classifier, there are more and even better such as the random forest. this classifier is considered the best among researchers, it uses a small number of random features, creating hundreds of decision trees using bootstrapping an bagging, this might work well, the number of the chosen features normally the sqrt of the feature vector size. those features are random. each decision tree converges to a solution, using majority rules the most likely class will chosen then.

Another solution is to use the dynamic time warping DTW, or even better to use Hidden Markov models HMM.

Another solution is the interpolation, interpolate (compensate for missing values along the small signal) all the small signals to be with the same size as the max signal, interpolation methods include and not limited to averaging, B-spline, cubic.....

Another solution is to use feature extraction method to use the best features (the most distinctive), this time make them fixed size, those method include PCA, LDA, etc.

another solution is to use feature selection (normally after feature extraction) an easy way to select the best features that give the best accuracy.

that's all for now, if non of those worked for you, please contact me.

blocks|key|1402377|text|为了在不同大小的图像上使用神经网络，图像本身通常会被裁剪和放大或缩小，以更好地适应网络的输入。我知道这并没有真正回答你的问题，但也许类似的事情也可以在其他类型的输入中实现，在输入上使用某种转换函数？|type|unstyled|depth|inlineStyleRanges|entityRanges|data|1402378|entityMap^0|0^^$0|@$1|2|3|4|5|6|7|D|8|@]|9|@]|A|$]]|$1|B|3|-4|5|6|7|E|8|@]|9|@]|A|$]]]|C|$]]

To use a neural net on images of different sizes, the images themselves are often cropped and up or down scaled to better fit the input of the network. I know that doesn't really answer your question but perhaps something similar would be possible with other types of input, using some sort of transformation function on the input?

All the examples I have seen of neural networks are for a fixed set of inputs which works well for images and fixed length data. How do you deal with variable length data such sentences, queries or source code? Is there a way to encode variable length data into fixed length inputs and still get the generalization properties of neural networks?

How are neural networks used when the number of inputs could be variable?

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

我见过的所有神经网络的例子都是针对一组固定的输入，这对图像和固定长度的数据都很有效。你如何处理可变长度的数据，如句子、查询或源代码？有没有一种方法可以将可变长度的数据编码成固定长度的输入，同时仍然获得神经网络的泛化特性？

问当输入的数量是可变的时，神经网络是如何使用的？
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

问当输入的数量是可变的时，神经网络是如何使用的？EN