Answers are grounded in this paper and cite their sources.
A linearly separable Boolean function is derived from a set of examples by a perceptron with optimal stability. The probability to reconstruct a pattern which is not learnt is calculated analytically using the replica method.
No takes yet. Share an insight, caveat, or question.
Opper et al. (1990) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: