TY - GEN
T1 - Analog computing for real-time solution of time-varying linear equations
AU - Jiang, Danchi
PY - 2004
Y1 - 2004
N2 - An implicit recurrent neural network model (IRNN) is proposed in this paper for solving on-line time-varying linear equations. Such a neural network can be implemented as analog circuits or VLSI. Excellent convergent properties have been revealed by careful theoretical analysis. In the specific case where the linear equation is obtained from a time-varying Sylvester equation, the proposed IRNN model coincides with some existing recurrent neural networks reported in recent literature, where simulation examples have been reported to demonstrate the effectiveness and efficiency.
AB - An implicit recurrent neural network model (IRNN) is proposed in this paper for solving on-line time-varying linear equations. Such a neural network can be implemented as analog circuits or VLSI. Excellent convergent properties have been revealed by careful theoretical analysis. In the specific case where the linear equation is obtained from a time-varying Sylvester equation, the proposed IRNN model coincides with some existing recurrent neural networks reported in recent literature, where simulation examples have been reported to demonstrate the effectiveness and efficiency.
KW - Implicit recurrent neural network
KW - Real-time computation
KW - Sylvester equation
KW - Time-varying linear equations
UR - http://www.scopus.com/inward/record.url?scp=11244333372&partnerID=8YFLogxK
M3 - Conference contribution
SN - 0780386477
SN - 9780780386471
T3 - 2004 International Conference on Communications, Circuits and Systems
SP - 1367
EP - 1371
BT - 2004 International Conference on Communications, Circuits and Systems
T2 - 2004 International Conference on Communications, Circuits and Systems
Y2 - 27 June 2004 through 29 June 2004
ER -