Sparse Distributed Memory Model Research Articles

Volume Signaling and Neural-Indexing by Nitric Oxide in Artificial Neural Networks

We present a computational study whose objective is to show the capacity of the Nitric Oxide (NO) diffusion for information recovery and indexing related to the classical neural architecture the Sparse Distributed Memory (SDM) has. The study is carried out by introducing NO diffusion dynamics by means of a Multi-compartment based NO Diffusion Model, in the storage process of the SDM. We develop a new SDM model, which we term Sparse Distributed Memory by Nitric Oxide diffusion (SDM-NO). Both of these architectures were computationally analysed. We have showed that the information indexing guided by the Nitric Oxide dynamics has a similar or slightly better behavior to the randomly guided by the SDM. For this study we have used two kinds of patterns, a) binary string patterns with eight bits and b) handwritten characters, that the indexing guided by the Nitric Oxide dynamics shows a similar or a little bit better behaviour to the guided indexing one performed randomly by the SDM. Nevertheless, we have also shown that both of the architectures do not perform well in these memory processes.

Relating number of processing elements in a sparse distributed memory model to learning rate and generalization

A simulated neural network was developed with APL on an 80386 microcomputer. The network was configured to associate task descriptions with 10 categories of military occupational specialties. The number of processing elements in the problem was varied. Increasing the number of processors increased the speed of learning in the simulation. Generalization was not significantly different for various numbers of processing elements except for one intermediate number at which generalization occurred about 15 percent higher. Analysis of the performance of a trained network suggests that low level, natural language understanding is one form of text processing which promises to become an important application area for neural model-based computing.

Character recognition in a sparse distributed memory

P. Kanerva's (1988) sparse distributed memory model is applied to character recognition. The results of recognizing corrupted characters, using a sparse distributed memory with fewer than 10000 locations, is described: 100 corrupted test patterns were generated to recognize 18 template patterns. The performance of the model is evaluated. Insights about the behavior of sparse distributed memories as well as the model's applicability to character recognition are provided. It was found that a sparse distributed memory of small size can recognize patterns with considerable noise.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>