Learning of correlated patterns by simple perceptrons

Abstract

Learning behavior of simple perceptrons is analyzed for a teacher-student scenario in which output labels are provided by a teacher network for a set of possibly correlated input patterns, and such that teacher and student networks are of the same type. Our main concern is the effect of statistical correlations among the input patterns on learning performance. For this purpose, we extend to the teacher-student scenario a methodology for analyzing randomly labeled patterns recently developed in {\em J. Phys. A: Math. Theor.} {\bf 41}, 324013 (2008). This methodology is used for analyzing situations in which orthogonality of the input patterns is enhanced in order to optimize the learning performance.

References in corpus (4)

• Learning by message-passing in networks of discrete synapses
• Inference from correlated patterns: a unified theory for perceptron learning and linear vector channels
• Perceptron capacity revisited: classification ability for correlated patterns
• Statistical mechanics of lossy compression using multilayer perceptrons

Cited by in corpus (10)

• Bayesian Optimal Data Detector for Hybrid mmWave MIMO-OFDM Systems with Low-Resolution ADCs
• Bayesian Optimal Data Detector for mmWave OFDM System with Low-Resolution ADC
• Mean-field inference methods for neural networks
• Generalized Turbo Signal Recovery for Nonlinear Measurements and Orthogonal Sensing Matrices
• Teacher-student learning for a binary perceptron with quantum fluctuations
• Macroscopic Analysis of Vector Approximate Message Passing in a Model Mismatch Setting
• Generalization from correlated sets of patterns in the perceptron
• Optimal Learning with Excitatory and Inhibitory synapses
• Active online learning in the binary perceptron problem
• Blind calibration for compressed sensing: State evolution and an online algorithm