a1 Department of Computing, City University London, Northampton Square, London, EC1V 0HB, United Kingdom
a2 Institute of Informatics, Federal University of Rio Grande do Sul, Brazil, Porto Alegre, RS, 91501-970, Brazil. Rafael.Borges.email@example.com http://www.soi.city.ac.uk/~Rafael.Borges.1 firstname.lastname@example.org http://www.soi.city.ac.uk/~aag LuisLamb@acm.org http://www.inf.ufrgs.br/~lamb
The target article criticises neural-symbolic systems as inadequate for analogical reasoning and proposes a model of analogy as transformation (i.e., learning). We accept the importance of learning, but we argue that, instead of conflicting, integrated reasoning and learning would model analogy much more adequately. In this new perspective, modern neural-symbolic systems become the natural candidates for modelling analogy.