Architecture of the proposed neural comparator, with intermediate layers x(2) and x(3) and output x(4). The comparator autonomously learns to compare the inputs y and z. The output is close to zero when the two inputs are
identical or correlated and close to unity when they are different or uncorrelated.
This site uses cookies. By continuing to use our website, you are agreeing to our privacy policy. No content on this site may be used to train artificial intelligence systems without permission in writing from the MIT Press.