Behavioral and Brain Sciences 31 (6):714-715 (2008)
AbstractWe argue that neural networks for semantic cognition, as proposed by Rogers & McClelland (R&M), do not acquire semantics and therefore cannot be the basis for a theory of semantic cognition. The reason is that the neural networks simply perform statistical categorization procedures, and these do not require any semantics for their successful operation. We conclude that this has severe consequences for the semantic cognition views of R&M
Added to PP
Historical graph of downloads
Citations of this work
Symbol Interdependency in Symbolic and Embodied Cognition.Max M. Louwerse - 2011 - Topics in Cognitive Science 3 (2):273-302.
Similar books and articles
Three Attitudes Towards Data Mining.Kevin D. Hoover & Stephen J. Perez - 2000 - Journal of Economic Methodology 7 (2):195-210.
Informational Privacy, Data Mining, and the Internet.Herman T. Tavani - 1999 - Ethics and Information Technology 1 (2):137-145.
I Am Not, nor Have I Ever Been a Member of a Data-Mining Discipline.Clinton A. Greene - 2000 - Journal of Economic Methodology 7 (2):217-230.
Introduction: Is Data Mining a Methodological Problem?Roger E. Backhouse & Mary S. Morgan - 2000 - Journal of Economic Methodology 7 (2):171-181.
Observations on the Practice of Data-Mining: Comments on the JEM Symposium.Steven Cook - 2001 - Journal of Economic Methodology 8 (3):415-419.
KDD, Data Mining, and the Challenge for Normative Privacy.Herman T. Tavani - 1999 - Ethics and Information Technology 1 (4):265-273.
Revisiting Data Mining: 'Hunting' with or Without a License.Aris Spanos - 2000 - Journal of Economic Methodology 7 (2):231-264.
Data Mining: Proprietary Rights, People and Proposals.Dinah Payne & Cherie Courseault Trumbach - 2009 - Business Ethics, the Environment and Responsibility 18 (3):241-252.