python - Backpropagation with Momentum using Scikit-Learn

Question

I'm trying to use Scikit-Learn's Neural Network to classify my dataset using a Backpropagation with Momentum. I need to specify these parameters: Hidden neurons, Hidden layers, Training set, Learning rate and Momentum. I found MLPClassifier in Sklearn.neural_network package. The problem is that this package is part of Scikit-learn V0.18 which is a dev version.

Is there a way I could use Scikit-Learn V0.17 to do this?

Using Anaconda, but I can change that if it causes problems.

Answer 1

如果有人需要这个问题的答案，我实际上决定在 Linux VM 上运行所有东西。然后我按照说明安装了开发版本，一切（几乎）都运行良好。在 Linux 上运行它比在 Windows 上容易得多，因为您可以从 git 安装包并运行它，而无需下载所需的软件来编译它。不过我还是有点挣扎。

Answer 2

另一种可能的解决方案是使用Google Colab。它们提供了一个可以导入 Scikit-Learn 工具包的环境。