Reducing transmission error effects using a self-organizing network

Bradburn,

doi:10.1109/ijcnn.1989.118294

Cited by 23 publications

(6 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Networks trained according to the above-described procedure were used for reducing the influence of errors in the transmission of a speech signal [11] and for classifying pattern sequences [99]. Luttrell [76] proposed a new formulation of the Kohonen self-organization that is convenient for problems of encoding.…”

Section: F Rn(t) + A(t)[x(t) -M(t)] I C Nomentioning

confidence: 99%

Neural networks as systems for recognizing patterns

Smetanin¹

1998

J Math Sci

View full text Add to dashboard Cite

1 This is the reason for the diversity of terms used to denote neural networks: coneural connectionist models, distributed systems, neuromorphous systems, recognition machines, associative memory. Suppose that the parameter p meets the conditions 0 < p < 1]2. The equilibrium state v is stable and possesses the attraction domain with radius pn if for any vector x such that Iv -x I < pn, I I is a network with the input vector x falling in the equilibrium position v. Here I I denotes the Hamming distance.Definition 3. Absolute stable capacity pM (n, p).For any e > 0, provided that m < p0,(n, p), the probability P{all m vectors are equilibrium states with attraction domain of radius pn} > 1 -e -o(1)}.Definition 4. Relative stable capacity pas(np).For any e > 0, provided that m < pos(n,p), the mean M{the number of vectors from the set that correspond to equilibrium states with attraction domain of radius pn} > m(1 -e -o(1)}. For nonrecurrent neural networks, the notion of equilibrium states loses its meaning, and the capacity is defined as the maximum value of input-output pairs which can be implemented with the use of the model considered. In this case, we can define the same types of capacity as for recurrent networks.Suppose that H= is a class of neural networks with n inputs from the region X,, with a single output from the region Y,, = {-1,1}. We also assume that VC-dim(Hn) = d,, and m samples of input and output signals are chosen independently in accordance with the distribution Dn within X~ x Y,~.Definition 5. The sequence pt,(n) is referred to as the lower capacity of the class H,~ if, for any arbitrarily small e > 0 and n --4 cr for any distribution D= the probability P{H,, implements all the specified relations between inputs and outputs} --* 1 provided that m < (1 -r Definition 6. The sequence pu(n) is referred to as the upper capacity of the class Hn if, for any arbitrarily small e > 0 and n --* o% for any distribution D~, the probability P{H,, implements all the specified relations between inputs and outputs} ~ 1 provided that m > (1 + e)pu(n).Definition 7. The sequence p(n) is called a capacity if it simultaneously satisfies the definitions of the lower and upper capacities.Stable capacities for nonrecurrent networks can be defined by analogy with recurrent networks. The notion of the capacity for nonrecurrent networks is closely associated with the Vapnik-Chervonenkis dimension.

show abstract

Section: F Rn(t) + A(t)[x(t) -M(t)] I C Nomentioning

confidence: 99%

Neural networks as systems for recognizing patterns

Smetanin¹

1998

J Math Sci

View full text Add to dashboard Cite

show abstract

“…Bradburn [5] suggested using the SOFM to reduce the effect of channel noise in p-law speech coding. He used the topology formed when each neuron forms one vertex of a hypercube, numbered such that neurons connected by a single edge differ in one bit.…”

Section: B Brad Burn's Hypercube Topologymentioning

confidence: 99%

A study on the effect of neighbourhood functions for noise robust vector quantisers

Andrew

Palaniswami

1994

Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94)

View full text Add to dashboard Cite

Abstruct-B y the use of noise robust compression, separate error correction can be reduced. This paper studies a number of neighbourhood functions for the SOFM for designing image vector quantiser codebooks for noisy channels. They include a neighbourhood recently proposed for the scalar coding of speech and a novel neighbourhood which makes the S O F M functionally equivalent to the popular LBG algorithm. The simulation results of these neighbourhood functions on t w o images provide insight into the problem of selecting an appropriate topology for the design of vector quantiser codebooks for noisy channels.

show abstract

“…routing, admission control, switching and mobile communications. Applications in the following areas will not be described in detail in this paper: coding theory [1][2][3][4][5][6], data transmission [7][8][9][10] and signal processing related to telecommunications [11][12][13][14][15][16][17]. We first introduce some basic neural network structures, i.e.…”

Section: Introductionmentioning

confidence: 99%