Difference between 2D input and multiple input with recurrent neural networks for time series
2 Ansichten (letzte 30 Tage)
Ältere Kommentare anzeigen
Nicolas M.
am 20 Jan. 2019
Kommentiert: Nicolas M.
am 27 Jan. 2019
Hi,
Note: Question edited in order to focus on the subject.
I'm using neural networks with 5 input time series of 3000 samples, to model 1 output time serie of 3000 samples. To do so, I used code generated thanks to the Neural Network toolbox for Time Series, and adapted it by using layrecnet. I use a 5x3000 matrix and a 1x3000 matrix to generate X (1x3000 cells of 5x1 double) and T (1x3000 cells of 1x1 double) with tonndata function followed by preparets before training. My network looks like this:
![](https://www.mathworks.com/matlabcentral/answers/uploaded_files/144985/image.png)
In network properties, it has only 1 input, which is a 2D dimensional input (since I have 5x1 double in each cell). I found this topic which explains how to use multiple inputs for a feed forward network. I then generated this 5 inputs network:
![](https://www.mathworks.com/matlabcentral/answers/uploaded_files/144986/image.png)
The only way I've been able to use this of network is by transforming by input_data into a 5x3000 cells and target into a 1x3000 cells. Which seems to be working fine, but training seems different from the previous one, with more frequent exit based on Mu threshold.
>> In my scenario, what are the pratical differences between the two pictured RNNS ?
I understand that second solutions allows for more freedom for each input (maybe delays, or the possibility to feed inputs to different layers), but is this useful in my scenario ?
Thank you in advance.
2 Kommentare
Greg Heath
am 21 Jan. 2019
Bearbeitet: Greg Heath
am 21 Jan. 2019
We can help you better if you illustrate your problem using MATLAB data
help layrecnet
doc layrecnet
Greg
Akzeptierte Antwort
Greg Heath
am 23 Jan. 2019
Written MATLAB should treat the cases the same.
Unfortunately I don't have time to prove it
Greg
Weitere Antworten (0)
Siehe auch
Kategorien
Mehr zu Sequence and Numeric Feature Data Workflows finden Sie in Help Center und File Exchange
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!