Parsing recursive sentences with a connectionist model including a neural stack and synaptic gating

Abstract

To cite this version:Anna Fedor, Péter Péter Ittzés, Eörs Eörs Szathmáry. Parsing recursive sentences with a connectionist model including a neural stack and synaptic gating. Journal of Theoretical Biology, Elsevier, 2011, 271 (1) This is a PDF file of an unedited manuscript that has been accepted for publication. As a service to our customers we are providing this early version of the manuscript. The manuscript will undergo copyediting, typesetting, and review of the resulting galley proof before it is published in its final citable form. Please note that during the production process errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal pertain. AbstractIt is supposed that humans are genetically predisposed to be able to recognize sequences of context free grammars with center-embedded recursion while other primates are restricted to the recognition of finite state grammars with tail-recursion. Our aim was to construct a minimalist neural network that is able to parse artificial sentences of both grammars in an efficient way without using the biologically unrealistic backpropagation algorithm. The core of this network is a neural stack-like memory where the push and pop operations are regulated by synaptic gating on the connections between the layers of the stack. The network correctly categorizes novel sentences of both grammars after training. We suggest that the introduction of the neural stack memory will turn out to be substantial for any biological 'hierarchical processor' and the minimalist design of the model suggests a quest for similar, realistic neural architectures.