King's College London

Research portal

Learning with incomplete information in the committee machine

Research output: Contribution to journalArticlepeer-review

Urs M. Bergmann, Reimer Kuehn, Ion-Olimpiu Stamatescu

Original languageEnglish
Pages (from-to)401 - 410
Number of pages10
JournalBiological Cybernetics
Issue number5-6
PublishedDec 2009

King's Authors


We study the problem of learning with incomplete information in a student-teacher setup for the committee machine. The learning algorithm combines unsupervised Hebbian learning of a series of associations with a delayed reinforcement step, in which the set of previously learnt associations is partly and indiscriminately unlearnt, to an extent that depends on the success rate of the student on these previously learnt associations. The relevant learning parameter lambda represents the strength of Hebbian learning. A coarse-grained analysis of the system yields a set of differential equations for overlaps of student and teacher weight vectors, whose solutions provide a complete description of the learning behavior. It reveals complicated dynamics showing that perfect generalization can be obtained if the learning parameter exceeds a threshold lambda (c) , and if the initial value of the overlap between student and teacher weights is non-zero. In case of convergence, the generalization error exhibits a power law decay as a function of the number of examples used in training, with an exponent that depends on the parameter lambda. An investigation of the system flow in a subspace with broken permutation symmetry between hidden units reveals a bifurcation point lambda* above which perfect generalization does not depend on initial conditions. Finally, we demonstrate that cases of a complexity mismatch between student and teacher are optimally resolved in the sense that an over-complex student can emulate a less complex teacher rule, while an under-complex student reaches a state which realizes the minimal generalization error compatible with the complexity mismatch.

View graph of relations

© 2020 King's College London | Strand | London WC2R 2LS | England | United Kingdom | Tel +44 (0)20 7836 5454