– Constructive algorithms are effective methods for designing Artificial Neural Networks (ANN) with good accuracy and generalization capability, yet with parsimonious network str...
Leonardo M. Holschuh, Clodoaldo Ap. M. Lima, Ferna...
For effective retrieval of visual information, statistical learning plays a pivotal role. Statistical learning in such a context faces at least two major mathematical challenges: ...
The problem of designing input signals for optimal generalization in supervised learning is called active learning. In many active learning methods devised so far, the bias of the...
This article is about a new approach in robotic learning systems. It provides a method to use a real-world device that operates in real-time, controlled through a simulated recurr...
This paper proposes an on-line error detecting method for a manually annotated corpus using min-max modular (M3 ) neural networks. The basic idea of the method is to use guaranteed...