Dynamics of learning with restricted training sets

Anthony C.C. Coolen, David Saad

Research output: Contribution to journalArticlepeer-review


The dynamics of supervised learning in layered neural networks were studied in the regime where the size of the training set is proportional to the number of inputs. The evolution of macroscopic observables, including the two relevant performance measures can be predicted by using the dynamical replica theory. Three approximation schemes aimed at eliminating the need to solve a functional saddle-point equation at each time step have been derived.

Original languageEnglish
Pages (from-to)5444-5487
Number of pages44
JournalPhysical Review E
Issue number4
Publication statusPublished - Oct 2000

Bibliographical note

Copyright of American Physical Society


  • layered neural networks
  • learning dynamics
  • dynamically replica theory


Dive into the research topics of 'Dynamics of learning with restricted training sets'. Together they form a unique fingerprint.

Cite this