[b]Speaker:[/b]
Lorenzo Sarti (Dipartimento di Ingegneria dell'Informazione - Università di Siena
[b]Abstract:[/b]
We present Similarity Neural Networks (SNNs), a neural network model able to learn a similarity measure for pairs of patterns, exploiting a binary supervision on their similarity/dissimilarity relationships. Pairwise relationships, referred to also as pairwise constraints, generally contain less information than class labels, but, in some contexts, are easier to obtain from human supervisors.