Recommendation for neural network implementation

Question

Veselin Manev 2021-4-13

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/801016-recommendation-for-neural-network-implementation

评论： Veselin Manev 2021-4-14

Hello,

I am relativly new to neural networks, but I want to design one, which can perform the following task:

I have two vectors with length N, which either do or do not contain certain property. I would like to train a neural network using many arrays, for which I know if this property is present or not. At the end, after introducing a new array (set of 2), it should be able to distinguish if this array has the predefined property and return true/false (of course with certain confidence).

I will be gratefull if you could give me directions/reading material on how to accomplish this.

Thank you

0 个评论
显示 -2更早的评论隐藏 -2更早的评论

请先登录，再进行评论。

请先登录，再回答此问题。

Answer 1

Jon Cherrie 2021-4-14

1
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/801016-recommendation-for-neural-network-implementation#answer_674741

It might be that you can solve this as sequence classification problem, e.g.,

https://www.mathworks.com/help/deeplearning/ug/classify-sequence-data-using-lstm-networks.html

It sounds like you can treat the two vectors of length N as a sequence of length N with two channels -- that would be the input to the network. Then the output would a classification of "property is present or not."