𝔖 Bobbio Scriptorium
✦   LIBER   ✦

A neural network for signal decomposition problems

✍ Scribed by Mauro Forti

Publisher
John Wiley and Sons
Year
1991
Tongue
English
Weight
673 KB
Volume
19
Category
Article
ISSN
0098-9886

No coin nor oath required. For personal study only.

✦ Synopsis

This paper presents the design of a neural network for signal decomposition problems with application examples. For this class of problems the proposed network has the same dynamics as the Hopfield net, but it is shown to realize the O ( M 2 ) connection paths among the M neurons with a number of wires and conductances increasing only linearly with increasing M , i.e. reducing this number by one dimension with respect to the quadratically increasing number of wires and conductances required in the Hopfield net.

Other advantages of the proposed neural network are discussed in relation to classical examples of decomposition problems. In particular, a new architecture for an N-bit A/D converter is presented employing 4 N conductances instead of the N ( N + 1) Hopfield A/D conductances.

πŸ“œ SIMILAR VOLUMES

A neural network approach to tiling prob
A neural network approach to tiling problems
✍ T. Tambouratzis πŸ“‚ Article πŸ“… 2001 πŸ› John Wiley and Sons 🌐 English βš– 123 KB

The family of tiling problems comprises combinatorial optimization problems involving a grid and a number of shapes. Appropriate placements of the shapes on the grid are sought such that specific constraints concerning shape overlap and grid coverage are satisfied. The family of tiling problems has

A neural network graph partitioning proc
A neural network graph partitioning procedure for grid-based domain decomposition
✍ C. C. Pain; C. R. E De Oliveira; A. J. H. Goddard πŸ“‚ Article πŸ“… 1999 πŸ› John Wiley and Sons 🌐 English βš– 300 KB πŸ‘ 2 views

This paper describes a neural network graph partitioning algorithm which partitions unstructured ΓΏnite element/volume meshes as a precursor to a parallel domain decomposition solution method. The algorithm works by ΓΏrst constructing a coarse graph approximation using an automatic graph coarsening me