The number of required hidden units is statistically estimated for feedforward neural networks that are constructed by adding hidden units one by one. The output error decreases w...
Online learning algorithms such as Winnow have received much attention in Machine Learning. Their performance degrades only logarithmically with the input dimension, making them us...
Abstract. Bidimensionality provides a tool for developing subexponential fixed-parameter algorithms for combinatorial optimization problems on graph families that exclude a minor....
Erik D. Demaine, Mohammad Taghi Hajiaghayi, Dimitr...
During the previous years, we presented several results concerned with various issues related to the correctness of models for business processes and services (i. e., interorganiza...
Code bloat, the excessive increase of code size, is an important issue in Genetic Programming (GP). This paper proposes a theoretical analysis of code bloat in the framework of sy...
Sylvain Gelly, Olivier Teytaud, Nicolas Bredeche, ...