[英]How to determine activation, loss, optimizer in keras while making artificial neural network
This is my dataframe 这是我的数据框
https://drive.google.com/file/d/1qAnyOkp_YayqzZ4i0CwqCTDiYTIOmv6I/view?usp=sharing https://drive.google.com/file/d/1qAnyOkp_YayqzZ4i0CwqCTDiYTIOmv6I/view?usp=sharing
I need to find the value of ra, last column of that dataset via the ANN 我需要通过ANN查找数据集的最后一列ra的值
I have used keras library to make that, here is my code 我已经使用keras库做到了,这是我的代码
https://gist.github.com/anonymous/9955247ad7341e5bc119556dead9fc71 https://gist.github.com/anonymous/9955247ad7341e5bc119556dead9fc71
But the y_pred
variable has set of 0s in output. 但是
y_pred
变量的输出设置为0。 Am I doing anything wrong with activation function? 我激活功能有问题吗?
I need to predict the ra values with training dataset 我需要使用训练数据集预测ra值
PS: I am a newbie to datascience and just I have started learning it via udemy PS:我是数据科学的新手,只是我已经开始通过udemy学习它
You can remove the second hidden layer as simple Ann is enough for this and also we don't have to use activator at the output layer as it is regression problem. 您可以删除第二个隐藏层,因为简单的Ann就足够了,并且我们也不必在输出层使用激活器,因为这是回归问题。
Please see the sample code https://github.com/naveenkambham/MachineLearningModels/blob/master/NeuralNetwork.py . 请参阅示例代码https://github.com/naveenkambham/MachineLearningModels/blob/master/NeuralNetwork.py 。 This is similar to your requirement.
这类似于您的要求。
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.