Reduced order multiport parallel and multidirectional neural associative memories
Loading...
Date
2009
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Biological Cybernetics
Abstract
This paper proposes multiport parallel and multidirectional
intraconnected associative memories of outer
product type with reduced interconnections. Some new
reduced order memory architectures such as k-directional
and k-port parallel memories are suggested. These architectures
are, also, very suitable for implementation of spatiotemporal
sequences and multiassociative memories. It is
shown that in the proposed memory architectures, a substational
reduction in interconnections is achieved if the actual
length of original N-bit long vectors is subdivided into k sublengths.
Using these sublengths, submemory matrices, Ts or
Ws , are computed, which are then intraconnected to form
k-port parallel or k-directional memories. The subdivisions
of N-bit long vectors into k sublengths save (k−1)×100
k % of
interconnections. It is shown, by means of an example, that
more than 80% reduction in interconnections is achieved.
Minimum limit in bits on k as well as maximum limit on
subdivisions in k is determined. The topologies of reduced
interconnectivity developed in this paper are symmetric in
structure and can be used to scale up to larger systems. The
underlying principal of construction, storage and retrieval
processes of such associative memories has been analyzed.
The effect of complexity of different levels of reduced interconnectivity
on the quality of retrieval, signal to noise ratio,
and storage capacity has been investigated. The model possesses
analogies to biological neural structures and digital
parallel port memories commonly used in parallel and multiprocessing
systems.
Description
Keywords
Neural Network Memories, Parallel Memory, Multidirectional Memory, Multi Associative Memory, Reduced Interconnections, Retrieval Issues
Citation
Biol Cybern (2009) 100:395–407