Show simple item record

dc.contributor.authorOmlin, Christian W.en_US
dc.contributor.authorGiles, C. Leeen_US
dc.date.accessioned2004-05-31T22:32:06Z
dc.date.available2004-05-31T22:32:06Z
dc.date.created1995-05en_US
dc.date.issued1998-10-15en_US
dc.identifier.urihttp://hdl.handle.net/1903/723
dc.description.abstractRecurrent neural networks that are {\it trained} to behave like deterministic finite-state automata (DFAs) can show deteriorating performance when tested on long strings. This deteriorating performance can be attributed to the instability of the internal representation of the learned DFA states. The use of a sigmoidal discriminant function together with the recurrent structure contribute to this instability. We prove that a simple algorithm can {\it construct} second-order recurrent neural networks with a sparse interconnection topology and sigmoidal discriminant function such that the internal DFA state representations are stable, i.e. the constructed network correctly classifies strings of {\it arbitrary length}. The algorithm is based on encoding strengths of weights directly into the neural network. We derive a relationship between the weight strength and the number of DFA states for robust string classification. For a DFA with $n$ states and $m$ input alphabet symbols, the constructive algorithm generates a ``programmed" neural network with $O(n)$ neurons and $O(mn)$ weights. We compare our algorithm to other methods proposed in the literature. Revised in February 1996 (Also cross-referenced as UMIACS-TR-95-50)en_US
dc.format.extent915072 bytes
dc.format.mimetypeapplication/postscript
dc.language.isoen_US
dc.relation.ispartofseriesUM Computer Science Department; CS-TR-3460en_US
dc.relation.ispartofseriesUMIACS; UMIACS-TR-95-50en_US
dc.titleConstructing Deterministic Finite-State Automata in Recurrent Neural Networksen_US
dc.typeTechnical Reporten_US
dc.relation.isAvailableAtDigital Repository at the University of Marylanden_US
dc.relation.isAvailableAtUniversity of Maryland (College Park, Md.)en_US
dc.relation.isAvailableAtTech Reports in Computer Science and Engineeringen_US
dc.relation.isAvailableAtUMIACS Technical Reportsen_US


Files in this item

Thumbnail
Thumbnail

This item appears in the following Collection(s)

Show simple item record