Synthesis of Multivalued Multithreshold Functions for CCD Implementation

Barr, Abd-El; Zaky,; Vranesic,

doi:10.1109/tc.1986.1676730

Cited by 19 publications

(5 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the theory of multiple-valued logic functions there is an important class of functions called multiple-valued multiplethreshold functions [1]. Such functions are used in the design of classes of multiple-valued logic circuits called programmable logic arrays [30].…”

Section: A Multiple-valued Logic Neural Networkmentioning

confidence: 99%

“…Such functions are used in the design of classes of multiple-valued logic circuits called programmable logic arrays [30]. A -valued -threshold function of one variable is defined as if if for if (1) where output vector; threshold vector with ; number of threshold values. A -input -valued -threshold perceptron [23], [40], [24], [41], abbreviated as -perceptron, computes a weighted -input -valued -threshold function given by (2) where input vector; …”

Section: A Multiple-valued Logic Neural Networkmentioning

confidence: 99%

“…A -perceptron can be decomposed into a two-hidden-layer network composed of input nodes, that is, one linear combiner in the first hidden layer, -perceptrons (usual linear threshold units) in the second hidden layer and one linear combiner in the output layer [1]. The transfer function of the -perceptron is expressed as the linear summation of linear threshold functions , that is…”

Section: A Multiple-valued Logic Neural Networkmentioning

confidence: 99%

“…1) Random Replacement: With some probability of mutation, each coordinate of a parent may be replaced in the following way: random (12) where random returns a random real number in the interval [ 1,1] with uniform probability.…”

Section: Mutationmentioning

confidence: 99%

See 3 more Smart Citations

STRIP - a strip-based neural-network growth algorithm for learning multiple-valued functions

Ngom

Stojmenović

Milutinović

2001

IEEE Trans. Neural Netw.

View full text Add to dashboard Cite

We consider the problem of synthesizing multiple-valued logic functions by neural networks. A genetic algorithm (GA) which finds the longest strip in V is a subset of K(n) is described. A strip contains points located between two parallel hyperplanes. Repeated application of GA partitions the space V into certain number of strips, each of them corresponding to a hidden unit. We construct two neural networks based on these hidden units and show that they correctly compute the given but arbitrary multiple-valued function. Preliminary experimental results are presented and discussed.

show abstract

Section: A Multiple-valued Logic Neural Networkmentioning

confidence: 99%

Section: A Multiple-valued Logic Neural Networkmentioning

confidence: 99%

Section: A Multiple-valued Logic Neural Networkmentioning

confidence: 99%

Section: Mutationmentioning

confidence: 99%

See 2 more Smart Citations

STRIP - a strip-based neural-network growth algorithm for learning multiple-valued functions

Ngom

Stojmenović

Milutinović

2001

IEEE Trans. Neural Netw.

View full text Add to dashboard Cite

show abstract

“…Depending on , we will either refer to real or logic ( )-perceptrons. It is well known that any -input -valued logic function can be transformed into a -valued -threshold function [1], [8] for some . Multiple-threshold devices [7] are threshold elements containing multiple levels of excitation (thresholds).…”

Section: Introductionmentioning

confidence: 99%

On the number of multilinear partitions and the computing capacity of multiple-valued multiple-threshold perceptrons

Ngom

Žunić²

2003

IEEE Trans. Neural Netw.

View full text Add to dashboard Cite

We introduce the concept of multilinear partition of a point set V/spl sub/R/sup n/ and the concept of multilinear separability of a function f:Vtwo head right arrowK={0,...,k-1}. Based on well-known relationships between linear partitions and minimal pairs, we derive formulae for the number of multilinear partitions of a point set in general position and of the set K(2). The (n,k,s)-perceptrons partition the input space V into s+1 regions with s parallel hyperplanes. We obtain results on the capacity of a single (n,k,s)-perceptron, respectively, for V subset R(n) in general position and for V=K(2). Finally, we describe a fast polynomial-time algorithm for counting the multilinear partitions of K(2).

show abstract

Multilevel storage memory using serial—parallel–serial charge—coupled device

Nakamura

1989

Electron Comm Jpn Pt II

View full text Add to dashboard Cite

Since the CCD can handle analog signals directly, it is used widely for delay lines, filters, imaging elements and imaging memories. This paper considers the multilevel storage memory of an SPS (serial‐parallel‐serial)‐CCD applied to field memories of image signals. First, a charge transfer model for an SPS‐CCD is created. By means of the transfer function derived from this model, it is clarified that the transfer losses of the serial register and the parallel register degrade the frequency characteristics of the amplitude and phase. It is pointed out that this degradation can be improved significantly by compensation of the transfer losses of the two serial registers and the parallel register. Since realization of a circuit for rigorous compensation of the transfer loss is extremely difficult, a simple transfer loss compensation method is also studied in which the SPS‐CCD is considered as a cascade connection of two serial registers. It is found that the difference in the effect of simple and rigorous compensations is at most 0.6 percent in the case of 50 percent eye degradation. Hence, the effectiveness of the simple compensation is confirmed. Also, by using a commercially available CCD, an experiment for eight‐level storage memory is carried out in which a simple transfer loss compensation is applied. It is confirmed that agreement of the calculated and measured signal error rates is excellent.

show abstract

Synthesis of Multivalued Multithreshold Functions for CCD Implementation

Cited by 19 publications

References 13 publications

STRIP - a strip-based neural-network growth algorithm for learning multiple-valued functions

STRIP - a strip-based neural-network growth algorithm for learning multiple-valued functions

On the number of multilinear partitions and the computing capacity of multiple-valued multiple-threshold perceptrons

Multilevel storage memory using serial—parallel–serial charge—coupled device

Contact Info

Product

Resources

About