How can I determine if I need a time series or a fitting neural network?
2 ビュー (過去 30 日間)
古いコメントを表示
I have been working a little with Neural Networks but I sometimes get confused when needing to choose between a Fitting Neural Network (nftool) and a Time Series Neural Network (ntstool).
I know that Time Series NN has to do with time and sequences, but as its aim is to predict values, wouldn't it be similar to create a Fitting NN? I mean, creating a generalized Fitting NN that can be used with more inputs that the already given, so that a "predicted" result can be obtained as well.
Which is the difference between them?
Thank you very much in advance for your time and help!
0 件のコメント
採用された回答
Greg Heath
2016 年 10 月 27 日
For a timeseries function points at neighboring times are highly correlated so that the autocorrelation function is nonrandom and/or inpnut and target points at neighboring times are highly correlated so that the corresponding crosscorrelation function is nonrandom.
For a fitting function only the input and target points at the same location are necessarily correlated. Random reordering of input/target pairs should make no difference,
Hope this helps.
Thank you for formally accepting my answer
Greg
その他の回答 (0 件)
参考
カテゴリ
Help Center および File Exchange で Sequence and Numeric Feature Data Workflows についてさらに検索
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!