Informational characteristics of neural networks capable of associative learning based on Hebbian plasticity

Frolov, A; Murav’ev, I. S.

doi:10.1088/0954-898x/4/4/006

Search citation statements

Order By: Relevance

Paper Sections

Select...

Other Pnn-architectures1

Citation Types

Supporting

Mentioning

Contrasting

Year Published

1998

2013

Publication Types

Select...

Article3

Book2

Other1

Relationship

Self Cite0

Independent6

Authors

Journals

Cited by 10 publications

(1 citation statement)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As it is known the memory capacity of Hopfield model falls down drastically if there are correlations, so the only way out is so named sparse coding [25]- [29]. Our method is an alternative to this approach.…”

Section: Other Pnn-architecturesmentioning

confidence: 99%

Vector-neuron models of associative memory

Kryzhanovsky¹,

Litinskii²,

Mikaelian³

2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541)

View full text Add to dashboard Cite

We consider two models of Hopfield-like associative memory with q-valued neurons: Potts-glass neural network (PGNN) and parametrial neural network (PNN). In these models neurons a n be in more than two different states. The models have the record characteristics of its storage capacity and noise immunity, and significantly exceed the Hopfield model. We present a uniform formalism allowing us to describe both PNN and PGNN. This networks inherent mechanisms, responsible for outstanding recognizing pmperties, are clarified.

show abstract

Section: Other Pnn-architecturesmentioning

confidence: 99%