I am trying to work on building a relationship in Keras, between X and Y where X= (1,30) and Y= (1,10).
I made model, to predict the Y from X. I am working in the biology field, and I want to predict the binary vector of Y through X with accuracy (90%) .
I will explain mode: X is a binary vector of length n (e.g., X(1,:) = [0/1, 0/1, ..., 0/1]).
Y is a binary vector of length m, where m < n (e.g., Y(1,:) = [0/1, 0/1, ..., 0/1]).
For each X => Y the data is like that : for example a sample :
X = [1,0,1,1,1,0,1,0,1,0,1,1,0,1] and its Y=[0,1,1,1,1,0,1]
My objective is to develop a machine learning model M that can predict the vector Y from the vector X with an accuracy greater than 90%. I accept only an error of 1 bit ! not more.
My question, what is the best cost function and loss function should I use ?
classificationandregression? To me, this is kind a “would a rose by any other name” situation, but I’d like the communication to be as smooth as possible. – Dave Jan 15 '24 at 19:28