5

I just created a VERY large neural net, albeit on very powerful hardware, and imagine my shock and disappointment, when I realized that NeuralFit[] from NeuralNetworks` package only seems to use one core, and not even to its fullest capacity. I was heartbroken. Do I really have to write an entire NN implementation from scratch? Or did I miss something simple?

My net took 200 inputs to 2 hidden layers of 300 neurons to produce 100 outputs. I understand we're talking about trillions of calculations, but as long as I know my hardware is the weak point - that can be upgraded. It should handle training of such a net fairly well if left alone for a while (4Ghz 8-thread machine with 24Gb of 2000Mhz CL7 memory running RAID-0 SSD drives on SATA-III - I'm fairly sure).

Ideas? Suggestions? Thanks in advance for your input.

4

3 回答 3

2

我是神经网络包的作者。给定输入，很容易并行化神经网络的评估。也就是说，在给定输入（以及所有权重，网络参数）的情况下计算网络的输出。但是，这种评估不是很耗时，并且对于大多数问题将其并行化也不是很有趣。另一方面，网络的训练通常很耗时，不幸的是，并行化并不容易。训练可以用不同的算法完成，最好的算法不容易并行化。我的联系信息可以在 Wolfram 网站上的产品主页上找到。非常欢迎改进建议。

如果您关闭建议栏（在首选项下），该软件包的最后一个版本在版本 9 和 10 中可以正常工作。原因是该软件包使用旧的 HelpBrowser 作为文档，并且与建议栏结合使用会崩溃。

你的乔纳斯

于 2014-11-27T12:43:53.197 回答
1

You can contact the author of the package directly, he is a very approachable fellow and might be able to make some suggestions.

于 2012-01-07T19:56:50.877 回答
0

我不确定您是如何编写代码的，或者它是如何在您使用的包中编写的；尝试使用矢量化，它确实加快了线性代数计算。在ml-class.org课程中，您可以看到它是如何制作的。

于 2012-01-18T17:21:43.040 回答