TY - GEN
T1 - Representation and induction of finite state machines using time-delay neural networks
AU - Clouse, Daniel S.
AU - Giles, C. Lee
AU - Horne, Bill G.
AU - Cottrell, Garrison W.
PY - 1997/1/1
Y1 - 1997/1/1
N2 - This work investigates the representational and inductive capabilities of time-delay neural networks (TDNNs) in general, and of two subclasses of TDNN, those with delays only on the inputs (IDNN), and those which include delays on hidden units (HDNN). Both architectures are capable of representing the same class of languages, the definite memory machine (DMM) languages, but the delays on the hidden units in the HDNN helps it outperform the IDNN on problems composed of repeated features over short time windows.
AB - This work investigates the representational and inductive capabilities of time-delay neural networks (TDNNs) in general, and of two subclasses of TDNN, those with delays only on the inputs (IDNN), and those which include delays on hidden units (HDNN). Both architectures are capable of representing the same class of languages, the definite memory machine (DMM) languages, but the delays on the hidden units in the HDNN helps it outperform the IDNN on problems composed of repeated features over short time windows.
UR - http://www.scopus.com/inward/record.url?scp=84899032195&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84899032195&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:84899032195
SN - 0262100657
SN - 9780262100656
T3 - Advances in Neural Information Processing Systems
SP - 403
EP - 409
BT - Advances in Neural Information Processing Systems 9 - Proceedings of the 1996 Conference, NIPS 1996
PB - Neural information processing systems foundation
T2 - 10th Annual Conference on Neural Information Processing Systems, NIPS 1996
Y2 - 2 December 1996 through 5 December 1996
ER -