A decomposition approach to multiclass classification problems consists in decomposing a multiclass problem into a set of binary ones. Decomposition splits the complete multiclass ...
We introduce and use a new methodology for the study of logics for action and change. The methodology allows one to define a taxonomy of reasoning problems, based in particular on...
High-throughput, data-directed computational protocols for Structural Genomics (or Proteomics) are required in order to evaluate the protein products of genes for structure and fu...
The fields of machine learning and mathematical programming are increasingly intertwined. Optimization problems lie at the heart of most machine learning approaches. The Special T...
— In connectionist learning, one relevant problem is “catastrophic forgetting” that may occur when a network, trained with a large set of patterns, has to learn new input pat...
Dario Albesano, Roberto Gemello, Pietro Laface, Fr...