# Recurrent neural network in 11.1 explicit examples?

I heard that RNN was implemented in Mathematica as of 11.1. Trying to search online, I find some general information about neural networks in Mathematica, or a list of related functions. My trouble is that this list of functions lumps purely statistical machine learning functions like Classify and Predict together with neural network functions, as well as (I presume) recurrent neural network functions, so that it is really hard to tell what it is I actually need to do RNN.

Perhaps there is a resource I missed that shows an explicit example of how to tackle a time series forecasting problem with several inputs, making use of Mathematicas RNN functions?

If none are known, perhaps someone knowledgeable could write a short example, e.g. using example data from here?

Thanks for any suggestion!

• Perhaps this YouTube video will help. youtu.be/dr3vAuFH5io Aug 30, 2017 at 22:55
• @m_goldberg Thank you, that was very helpful indeed! Even though the video did not address any cases in which the sequence has continuity properties in the mathematical sense, I am starting to suspect that this property is implied to be captured by these techniques without doing anything extra. Aug 30, 2017 at 23:48

Here is a simple example that may help you get started. In this example, we are going to a predict a simple time series of a sinusoid wave.

data = Table[Sin[x], {x, 0, 100, 0.04}]; We will cut the data into windows of 51 data points. The first 50 points as a whole is our X, and the last data point is our Y.

training =
RandomSample[
List /@ Most[#] -> List@Last[#] & /@ (Partition[data, 51, 1])];


We use a single gated recurrent layer in our neural network

net = NetChain[{
GatedRecurrentLayer,
LinearLayer}, "Input" -> {50, 1}, "Output" -> 1
]


and train with the training data

trained = NetTrain[net, training]


After training, we can use it to predict the time series. We first feed the neural network with 50 data points and then repeatedly use the data it generates to feed back into the neural network to generate the next data point. Here is a comparison between the ground truth and our predictions, which shows very good agreements.

ListPlot[{Flatten@
NestList[Append[Rest[#], trained[#]] &,
List /@ Sin[Range[-49*0.04, 0, 0.04]], 500][[All, -1]],
Table[Sin[x], {x, 0, 500*0.04, 0.04}]}, Joined -> True,
PlotLegends -> {"predicted", "ground truth"}] • This looks interesting! What should be changed if we have more features than just the observable itself? Do I understand correctly, that we would need to predict each feature as well as the observable (plus 49 past steps) in order to make a second prediction step, and so forth, in this case? --- (for the sake of example, maybe you could just duplicate the data and feed it as several features in parallel, to illustrate the syntax?) Aug 30, 2017 at 20:31
• Also, which criterium tells you that you should use only one layer, and with exactly 10 nodes? Aug 30, 2017 at 20:34
• I decided to accept this answer because it made the syntax most clear and gave me the ability to write my own code. Aug 31, 2017 at 12:58
• @Kagaratsch For multiple inputs, the first thing you can try is to use CatenateLayer to join the three input into a long sequence before feeding it into the recurrent layers. For example, something like:NetGraph[{CatenateLayer[], GatedRecurrentLayer, LinearLayer}, {{NetPort["Input1"], NetPort["Input2"], NetPort["Input3"]} -> 1, 1 -> 2 -> 3}, "Input1" -> {50, 1}, "Input2" -> {50, 1}, "Input3" -> {50, 1}, "Output" -> 1], where input1,2,3,4 can be your par1,2,3 and obs. Aug 31, 2017 at 14:18
• I set the number of layers and number of neurons by trail and error. But in general, increase the number of neurons will make the network more powerful to capture the features in the data, but it is also prone to overfitting and requires more data to train. Aug 31, 2017 at 14:26

Taking inspiration from the answer by xslittlegrass, I came up with the following solution.

Recall the sample data from this question. We have an observable obs we are interested to predict: and three parameters par1, par2, par3 that are correlated with the observable to some extent: We only use the data for the first 700 time steps to train the model, and will try to predict the next 300 time steps.

We create a training set of tlen consecutive data points of length featn each, which have the respectively following data point of length featn as output. Then we train a model that returns featn outputs:

dat = Transpose[{par1/Max[par1], par2/Max[par2], par3/Max[par3], obs/Max[obs]}];
tlen = 300; featn = Length[dat[]];
training = Table[dat[[i ;; i + tlen - 1]] -> dat[[i + tlen]], {i, 1, Length[dat] - tlen}];
net = NetChain[{GatedRecurrentLayer[tlen, "Dropout" -> {"VariationalInput" -> 0.1 , "VariationalState" -> 0.5}], LinearLayer[featn]}, "Input" -> {tlen, featn}, "Output" -> {featn}]
trained = NetTrain[net, training, Method -> {"ADAM", "InitialLearningRate" -> 0.0001}]


The training takes about two minutes. Finally, we can iteratively predict the future 300 steps

datt = dat;
Dynamic[i]
Do[
start = datt[[-tlen ;;]];
AppendTo[datt, trained[start]];
, {i, 1, 300}]


Amazingly, the prediction is qualitatively correct, with amplitude deviation growing to about 15% over the course of 300 time steps!

ListPlot[{datt[[;; , 4]], tab}] Any suggestions for how to improve upon the above?

• Add dropout ("VariationalInput"-> 0.1 and "VariationalState"-> 0.5) ,(try different values) showed that also during training tweek with learningRate (try from 0.1 to 0.0001 and see you get an improvement. Aug 31, 2017 at 10:46
• @user34018 Thanks! Those options helped improve the prediction quite a bit! Aug 31, 2017 at 12:18
• tab is not defined in the ListPlot code. You can include it for the sake of completeness. Aug 31, 2017 at 13:50
• @PlatoManiac I added tab to the data at gist.github.com/anonymous/8b65b221a1eef1afd9b8491d61283b0f Aug 31, 2017 at 17:29

For instance, let's assume you have a sequence of 3 and you have 8 input variables (features) X

Let Y be the output with values "yes" or "no" for each sequence of X

Let's X have a dimension of 195

You create a sequence of 3 for X

Xpartition = Partition[X, 3]


Now, you create your trainingData:

trainingData = MapThread[Rule, {Xpartition, Y}]


net = NetChain[
{ LongShortTermMemoryLayer
, SequenceLastLayer[]
, LinearLayer
, SoftmaxLayer[]
}
, "Input" -> {3, 8}
, "Output" -> NetDecoder[{"Class", {"no", "yes"}}]
]


where 3 is the number of vectors in the sequence, and 8 is the length of vectors.

• Thank you for your hints! May I ask a few questions? By sequence of 3 you mean, your time series has 3 consecutive time steps? What is the dimension 195 of X, I do not see it enter the code anywhere? You do not define any Y, what is it? What are all the SequenceLastLayer, LinearLayer and SoftmaxLayer for, why do they appear in this order in the syntax? A yes or no output is not really what I'd like to learn how to do, rather I'd like to predict the next value in a sequence of values of an observable, that also enters as one of the features. Could you use the data from my question? Aug 30, 2017 at 11:41
• Basically, I still do not see any consecutive time steps in the answer and how to predict the next one. What I am looking for is a worked example like the following, except for Mathematica: machinelearningmastery.com/… In the end, if no humanly comprehensible examples exist for how to use this functionality in Mathematica, I'll just end up using tensorflow, which would be sad... Aug 30, 2017 at 11:45
• In my problem, I have to predict device failure. I have a device is monitored by 8 variables. All these variables are connected to time. To use RNN, I have to decide my sequence that will predict failure (as I have more than one variables so instead of having xt-1, xt-2, xt-3 where x is just one data point, I have each xt with 8 data points, but I still want to predict failure using all these variables. Therefore, I have to provide RNN with my sequence that has all (xt-1, xt-2,xt-3). By the way, this gave me great results. Aug 31, 2017 at 10:37
• 195 is my sample size Aug 31, 2017 at 10:47

Key applied RNN examples from developers are located in documentation at:

http://reference.wolfram.com/language/tutorial/NeuralNetworksOverview.html

See "Sequence Learning and NLP" section.

• I have seen these examples before. integer addition, sorting sequences, question answering, language modeling, sentiment analysis - none of these address my questions, sadly. Aug 30, 2017 at 21:09
• As a note, this page does not exist anymore. May 17, 2019 at 14:30
• @dearN URL corrected, thanks. May 17, 2019 at 16:24

Here RNN in Mathematica? they are talking about RNN

In help section, if you for LongShortTermMemoryLayer you will also find other RNN models that have been implemented.

• As far as I understand, a LongShortTermMemoryLayer is just a basic building block that can be part of a model. However, there does not seem to be a comprehensive example on how to use it in a concrete model e.g. to generate a forecast of several time steps of an observable based on several input parameters. Aug 30, 2017 at 2:05
• The example they present using LongShortTermMemoryLayer, SequenceLastLayer[], LinearLayer Aug 30, 2017 at 2:31
• There they are doing addition with strings, which has no time series properties. It is still unclear how to take a time flow into account and generate a forecast. Aug 30, 2017 at 4:16
• You are supposed to have a sequence of vectors of size k, where each vector contains your several inputs (predictors, also called independent variables or features). So your input will be defined as "input"-> {k,length_of_vector} Aug 30, 2017 at 9:58