VLSI
implementation of a neural network for solving linear second order
parabolic PDE
- Moon, S.T.; Xia, B.; Spencer, R.G.; Gunhee Han;
Sanchez-Sinencio, E.
Dept. of Electr. Eng., Texas A&M; Univ., College Station, TX, USA
This paper appears in: Circuits and Systems, 2000.
Proceedings of the 43rd IEEE Midwest Symposium on
On page(s): 836 - 839 vol.2
8-11 Aug. 2000
Lansing, MI, USA
2000
Volume: 2
ISBN: 0-7803-6475-9
IEEE Catalog Number: CH37144
Number of Pages: 3 vol.xlix+1437
References Cited: 6
INSPEC Accession Number: 7174988
Abstract:
Proposes an implementation of a cellular neural network to
solve linear second order parabolic partial differential equations.
This paper describes the underlying theory, circuit architecture and
techniques employed to improve accuracy and throughput. A modified
time-multiplexing scheme is applied to provide an area efficient
solution. Simulation results and comparison are also included to
illustrate the circuit performance.
Index Terms:
VLSI; cellular neural nets; partial differential equations;
time division multiplexing; neural chips; VLSI; cellular neural
network; linear second order parabolic partial differential equations;
circuit architecture; accuracy; throughput; time-multiplexing scheme;
area efficient solution; circuit performance