Perceptron capacity revisited: classification ability for correlated patterns
Takashi Shinzato, Yoshiyuki Kabashima · Journal of Physics A Mathematical and Theoretical · 2008
In this paper, we address the problem of how many randomly labeled patterns can be correctly classified by a single-layer perceptron when the patterns are correlated with each other. In order to solve this problem, two analytical schemes are developed based on the replica method and the Thouless–Anderson–Palmer (TAP) approach by utilizing an integral formula concerning random rectangular matrices. The validity and relevance of the developed methodologies are shown for one known result and two example problems. A message-passing algorithm to perform the TAP scheme is also presented.