blocks|key|1584179|text|不是太技术性，但我非常确定一堆连接的循环产生的一系列循环可以产生内存。|type|unstyled|depth|inlineStyleRanges|entityRanges|data|1584180|每个循环都允许数据循环，下面的每个循环都可以识别、检索或修改内存。|1584181|当然，我不确定您将如何诱使网络纳入这种设计。|1584182|entityMap^0|0|0|0^^$0|@$1|2|3|4|5|6|7|H|8|@]|9|@]|A|$]]|$1|B|3|C|5|6|7|I|8|@]|9|@]|A|$]]|$1|D|3|E|5|6|7|J|8|@]|9|@]|A|$]]|$1|F|3|-4|5|6|7|K|8|@]|9|@]|A|$]]]|G|$]]

Not to be too nontechnical, but I'm pretty sure a series of loops coming off of a bunch of connected loops could produce memory.

Each loop would allow data to circle, and each loop underneath could identify, retrieve, or modify the memory.

Of course, I'm not sure how you would entice the network to incorporate that design.

blocks|key|470542|text|你要做的并不是什么问题，神经网络真的很擅长，因为它们更擅长泛化模式，而不是学习它们。但是，您可以使用概率神经网络或常规感知来实现这一点。你对你的问题有点含糊其辞，所以我不得不含糊其辞地回答。我假设您的意思是传入内存数据，然后将其“分类”到一个内存地址。这样，当您使用监督训练方法训练网络时，您将能够传递与现有项目相似或相同的内存数据，网络将为您提供地址。我想你也可以反过来做同样的事情。|type|unstyled|depth|inlineStyleRanges|entityRanges|data|470543|如果你使用概率神经网络，你基本上会学习你传递给网络的每一个模式。当然，每次您想要存储一个新的内存地址时，都会向网络中添加一个新的节点，这会使事情变得有点低效。已经做了一些工作来减少这个问题，for+example,+this+paper+(你必须自己实现算法)。也许这种类型的网络在准确地“记住”记忆的同时仍然能够概括结果(使用概率)是最可靠的。缺点是它将是内存密集型的。|offset|length|470544|传统的前馈、反向传播网络(感知器)也应该允许你这样做。但是，您必须小心创建足够的隐藏节点，以允许网络正确地调用所有输入值。这样做当然会导致过度拟合，但听起来你不想对输入数据进行泛化，你想更好地回忆模式。|470545|要解决学习新数据的问题，您只需使您的网络能够随着时间的推移而学习，而不是一次学习。您必须对此进行更多的研究，但您需要使用某种在线学习算法。|470546|总而言之，不要使用神经网络，使用其他类型的算法:p|style|BOLD|470547|entityMap|0|LINK|mutability|MUTABLE|url|http://www.sciencedirect.com/science/article/pii/S0925231297000635^0|0|2N|N|0|0|0|0|0|P|0^^$0|@$1|2|3|4|5|6|7|V|8|@]|9|@]|A|$]]|$1|B|3|C|5|6|7|W|8|@]|9|@$D|X|E|Y|1|Z]]|A|$]]|$1|F|3|G|5|6|7|10|8|@]|9|@]|A|$]]|$1|H|3|I|5|6|7|11|8|@]|9|@]|A|$]]|$1|J|3|K|5|6|7|12|8|@$D|13|E|14|L|M]]|9|@]|A|$]]|$1|N|3|-4|5|6|7|15|8|@]|9|@]|A|$]]]|O|$P|$5|Q|R|S|A|$T|U]]]]

What you're trying to do isn't a problem neural networks are really that great at since they're better at generalizing patterns, not learning them. However you may be able to accomplish this with either probabilistic neural networks or a regular perception. You were a little vague about your problem, so I'll have to be vague about my answer. I'm going to assume you mean that you pass in memory data and then "classify it" to a memory address. This way when you train the network using a supervised training method you will be able to pass in memory data that is similar or the same as an existing item and the network will give you the address. You could also do the same thing in reverse I suppose.

If you use a probabilistic neural network you'll essentially be learning every single pattern you pass to the network. Of course then every time you want to store a new memory address, you're adding a new node to the network, which makes things a little inefficient. Work has been done to reduce this problem, <a href="http://www.sciencedirect.com/science/article/pii/S0925231297000635" rel="nofollow">for example, this paper</a> (you would have to implement the algo yourself). Perhaps this type of network would be most reliable in "remembering" the memory accurately, while still being able to generalize the results (using probabilities). The downside is that it will be memory intensive.

Traditional feedforward, backpropogation networks (perceptrons) should also allow you to do something like this. However you're going to have to be careful to create enough hidden nodes to allow the network to properly recall all your input values. Doing this will of course cause over fitting, but it sounds like you don't want to generalize your input data, you want better recall for patterns.

To solve the problem of learning new data, you'll just need to make your network able to learn over time, instead of learning once. You'll have to research this more, but you'll want to use some sort of online learning algorithm.

In conclusion, don't use neural networks, use some other kind of algorithm :p

blocks|key|470580|text|Hopfield+neural+network是实现联想记忆的一种简单方法。方便的是，它甚至得到了Encog框架的支持。|type|unstyled|depth|inlineStyleRanges|entityRanges|offset|length|data|470581|entityMap|0|LINK|mutability|MUTABLE|url|http://en.wikipedia.org/wiki/Hopfield_neural_network^0|0|N|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]]]]

The <a href="http://en.wikipedia.org/wiki/Hopfield_neural_network" rel="nofollow">Hopfield neural network</a> is a simple way of implementing associative memory. Conveniently, it is even supported by the Encog framework.

I want to mimic computer memory with jeff heaton's encog neural network library. I just don't know what approach to use.

My requirement is to, have a memory location and a collection of bytes for the values.

<pre><code>location [0000]:byte-data[0101010]
location [0001]:byte-data[0101010]
</code></pre>

Those are the values I pass to the neural network system.

I was trying to avoid retraining the neural network every time the memory data changes. But maybe that is what I need to do. 

What neural network techniques would you use to accomplish what I am trying to do?

Neural-network (with Jeff Heaton's Encog) to mimic computer memory

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

我想用jeff heaton的encog神经网络库模拟计算机内存。我只是不知道该用什么方法。我的要求是，有一个内存位置和一个值的字节集合。location [0000]:byte-data[0101010]location [0001]:byte-data[0101010]这些是我传递给神经网络系统的值。我试图避免每次...

问神经网络(使用Jeff Heaton的Encog)来模拟计算机内存
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

问神经网络(使用Jeff Heaton的Encog)来模拟计算机内存EN