– This paper proposes a knowledge-based neurocomputing approach to extract and refine a set of linguistic rules from data. A neural network is designed along with its learning al...
Abstract. The O-OSCAR software architecture is a problem solving environment for complex scheduling problem that is based on a constraintbased representation. On top of this core r...
We present new fingerprint classification algorithms based on two machine learning approaches: support vector machines (SVMs), and recursive neural networks (RNNs). RNNs are traine...
Yuan Yao, Gian Luca Marcialis, Massimiliano Pontil...
This paper presents a novel method for wide coverage parsing using an incremental strategy, which is psycholinguistically motivated. A recursive neural network is trained on treeba...
Fabrizio Costa, Vincenzo Lombardo, Paolo Frasconi,...
The exponential growth of documents available in the World Wide Web makes it increasingly difficult to discover relevant information on a specific topic. In this context, growing ...