neural network - What is the way to feed multidimensional input data to encog ANN in java? -


i trying feed input (ip) v/s ideal (id) data encog neural network (basicnetwork class). tutorials show input format (mldata) this:

ip11,ip12,ip13        id11,id12 ip21,ip22,ip23        id21,id22 more values... 

but want feed data this:

ip11,ip12,ip13 ip21,ip22,ip23        id11,id12  ip11,ip12,ip13 ip21,ip22,ip23        id21,id22 

basically intend associate matrix of input values array of ideal values. there way using encog framework?

eagerly awaiting reply.

nearly machine learning models, neural networks included, accept vector (one dimension) input. way represent such 2d (or higher dimensional) data basicnetwork (in encog) flatten matrix vector. 8x8 matrix 64-element vector. traditional feedforward neural network (basicnetwork), not matter part of matrix maps element in input vector. fact input #3 , input #4 next each other not matter, separate.


Comments

Popular posts from this blog

asp.net mvc - SSO between MVCForum and Umbraco7 -

Python Tkinter keyboard using bind -

ubuntu - Selenium Node Not Connecting to Hub, Not Opening Port -