Verifiquei hoje que o artigo Statistical Mechanics of Online Learning of Drifting Concepts: A Variational Approach, de Renato Vicente, Osame Kinouchi and Nestor Caticha (1998) está com acesso liberado no site da Springer. Este artigo é uma das pérolas subestimadas dos bons tempos em que pesquisávamos redes neurais artificiais. Me orgulho do artigo, pela qualidade, pela revista onde foi publicado e por ser meu único paper em colaboração com Renato Vicente.
Abstract We review the application of statistical mechanics methods to the study of online learning of a drifting concept in the limit of large systems. The model where a feed-forward network learns from examples generated by a time dependent teacher of the same architecture is analyzed. The best possible generalization ability is determined exactly, through the use of a variational method. The constructive variational method also suggests a learning algorithm. It depends, however, on some unavailable quantities, such as the present performance of the student. The construction of estimators for these quantities permits the implementation of a very effective, highly adaptive algorithm. Several other algorithms are also studied for comparison with the optimal bound and the adaptive algorithm, for different types of time evolution of the rule.