๐”– Bobbio Scriptorium
โœฆ   LIBER   โœฆ

Clustering with neural networks

โœ Scribed by Behzad Kamgar-Parsi; J. A. Gualtieri; J. E. Devaney; Behrooz Kamgar-Parsi

Publisher
Springer-Verlag
Year
1990
Tongue
English
Weight
759 KB
Volume
63
Category
Article
ISSN
0340-1200

No coin nor oath required. For personal study only.

โœฆ Synopsis

Partitioning a set of N patterns in a d-dimensional metric space into K clusters -in a way that those in a given cluster are more similar to each other than the rest -is a problem of interest in many fields, such as, image analysis, taxonomy, astrophysics, etc. As there are approximately KS/K! possible ways of partitioning the patterns among K clusters, finding the best solution is beyond exhaustive search when N is large. We show that this problem, in spite of its exponential complexity, can be formulated as an optimization problem for which very good, but not necessarily optimal, solutions can be found by using a Hopfield model of neural networks. To obtain a very good solution, the network must start from many randomly selected initial states. The network is simulated on the MPP, a 128 x 128 SIMD array machine, where we use the massive parallelism not only in solving the differential equations that govern the evolution of the network, but also in starting the network from many initial states at once thus obtaining many solutions in one run. We achieve speedups of two to three orders of magnitude over serial implementations and the promise through Analog VLSI implementations of further speedups of three to six orders of magnitude.

๐Ÿ“œ SIMILAR VOLUMES

Clustering with artificial neural networ
Clustering with artificial neural networks and traditional techniques
โœ G. Tambouratzis; T. Tambouratzis; D. Tambouratzis ๐Ÿ“‚ Article ๐Ÿ“… 2003 ๐Ÿ› John Wiley and Sons ๐ŸŒ English โš– 178 KB

In this article, two clustering techniques based on neural networks are introduced. The two neural network models are the Harmony theory network (HTN) and the self-organizing logic neural network (SOLNN), both of which are characterized by parallel processing, a distributed architecture, and a large

Activation clustering in neural and soci
Activation clustering in neural and social networks
โœ Marko Puljic; Robert Kozma ๐Ÿ“‚ Article ๐Ÿ“… 2005 ๐Ÿ› John Wiley and Sons ๐ŸŒ English โš– 153 KB

## Abstract Questions related to the evolution of the structure of networks have received recently a lot of attention in the literature. But what is the state of the network given its structure? For example, there is the question of how the structures of neural networks make them behave? Or, in the

Bidirectional clustering of weights for
Bidirectional clustering of weights for neural networks with common weights
โœ Kazumi Saito; Ryohei Nakano ๐Ÿ“‚ Article ๐Ÿ“… 2007 ๐Ÿ› John Wiley and Sons ๐ŸŒ English โš– 445 KB

## Abstract This paper proposes a method which succinctly structures neural networks having a few thousand weights. Here structuring means weight sharing where weights in a network are divided into clusters and weights within a cluster have the same value. We newly introduce a weight sharing techni