Using LSTM to predict Random Numbers from Java's Random() class

sqljunkey · January 3, 2021, 9:49pm

Hi, I was interested to try using LSTM to predict Random numbers from Java’s Random class. I use random.getNextDouble() which gives you a random number between 0 and 1. I put these results in one sequence file for the features, and the next number from the sequence in a target file. I trained the network on this data and then evaluated with regression. What I find is the Rsquared is low etc. Am I doing something wrong here? Is it even possible to do this with random data?

This is the code: import org.bytedeco.opencv.opencv_face.FacemarkAAM;import org.datavec.api.re - Pastebin.com (which is just one of the examples updated to work)
This is the code for the random generator: import lombok.val;import org.apache.commons.io.FileUtils;import java.io. - Pastebin.com

Thanks

Topic		Replies	Views
LSTM Regression Example DL4J	11	1113	January 13, 2022
A post in "Weird results from my LSTM prediction" requires staff attention DL4J	2	402	January 11, 2021
Getting output prediction for LSTM DL4J	3	533	September 24, 2022
DL4J Need help with my input data DL4J	5	454	December 25, 2020
Questions for Time Series LSTM DL4J	20	2008	February 26, 2020

Using LSTM to predict Random Numbers from Java's Random() class

Related topics