Hardware implementation of a CNN for analog simulation of reaction-diffusion equations

Bonaiuto, V.; Maffucci, Antonio; Miano, G.; Salerno, Mário Sérgio; Sargeni, F.; Serra, Paul; Visone, C.

doi:10.1109/iscas.2001.921353

Cited by 7 publications

(3 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The new circuit presented in this paper is a CNN dedicated to the solution of RD-PDE with the capability to use either the FD or FE discretization methodologies [9]. In order to test this new multi-method feature, we prefer to design a prototype chip able to solve one-dimensional problems only.…”

Section: The Cellular Non-linear Networkmentioning

confidence: 99%

Programmable CNN Analogue Chip for RD-PDE Multi-Method Simulations

Sargeni

Bonaiuto

2005

Analog Integr Circ Sig Process

View full text Add to dashboard Cite

show abstract

Section: The Cellular Non-linear Networkmentioning

confidence: 99%

Programmable CNN Analogue Chip for RD-PDE Multi-Method Simulations

Sargeni

Bonaiuto

2005

Analog Integr Circ Sig Process

View full text Add to dashboard Cite

show abstract

“…Reference [3]). In some cases, such CNNs have also been implemented through dedicated chips [4] or through more exible systems, such as the CNN Universal Machine [5]. Concerning the approximate minimization of functionals, in two recent papers [6,7], a method (based on the theory of potential functions for resistive circuits) for the deÿnition of CNNs that ÿnd approximate minima of rather a large class of continuous functionals has been proposed.…”

Section: Synthesis Of Cellular Non-linear Networkmentioning

confidence: 99%

“…The ÿ-basis is not orthogonal in terms of any of the two considered deÿnitions of inner product (i.e. either (4) or (5)), but it is precious from the circuit-synthesis point of view, as the functions p can be easily implemented by resorting to proper elementary circuit blocks (see Section 4).…”

Section: ÿ-Basismentioning

confidence: 99%

A method for the approximate synthesis of cellular non‐linear networks—Part 1: Circuit definition

Storace

Repetto

Parodi

2003

Circuit Theory & Apps

View full text Add to dashboard Cite

SUMMARYIn this paper, we face the problem of the synthesis of cellular non-linear networks (CNNs) able to ÿnd approximate solutions of either partial di erential equations or functional minimization problems. In particular, the paper deals with the approximate synthesis of the multi-terminal resistors that include all the non-linearities of such dynamic circuits. The proposed approximation method is based on the piecewise-linear (PWL) approach developed by JuliÃ an et al. in the last few years, but it resorts to a di erent deÿnition of the inner product and hence to other PWL basis functions. The method is applied to a case-study concerning a CNN devoted to image processing.

show abstract