Behavioral and Brain Sciences



Short Communication

Hidden Markov model interpretations of neural networks


Ingmar Visser a1
a1 Developmental Psychology Institute of the University of Amsterdam, 1018 WB Amsterdam, The Netherlands ingmar@dds.nl http://develop.psy.uva.nl/users/ingmar/op_visser@macmail.psy.uva.nl

Abstract

Page's manifesto makes a case for localist representations in neural networks, one of the advantages being ease of interpretation. However, even localist networks can be hard to interpret, especially when at some hidden layer of the network distributed representations are employed, as is often the case. Hidden Markov models can be used to provide useful interpretable representations.



Metrics