Information storage and effective data retrieval in sparse matrices

Bentz, H.; Hagstroem, M.; Palm, Günther

doi:10.1016/0893-6080(89)90038-5

Cited by 32 publications

(11 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One way to make patterns orthogonal is to generate a very sparse representation of them (Bentz et al, 1989). This means that they are encoded such that only few units are significantly active at a time.…”

Section: Catastrophic Interferencementioning

confidence: 99%

A functional hypothesis for adult hippocampal neurogenesis: Avoidance of catastrophic interference in the dentate gyrus

2006

View full text Add to dashboard Cite

The dentate gyrus is part of the hippocampal memory system and special in that it generates new neurons throughout life. Here we discuss the question of what the functional role of these new neurons might be. Our hypothesis is that they help the dentate gyrus to avoid the problem of catastrophic interference when adapting to new environments. We assume that old neurons are rather stable and preserve an optimal encoding learned for known environments while new neurons are plastic to adapt to those features that are qualitatively new in a new environment. A simple network simulation demonstrates that adding new plastic neurons is indeed a successful strategy for adaptation without catastrophic interference.

show abstract

Section: Catastrophic Interferencementioning

confidence: 99%

A functional hypothesis for adult hippocampal neurogenesis: Avoidance of catastrophic interference in the dentate gyrus

2006

View full text Add to dashboard Cite

show abstract

“…In addition, neural associative memories are potentially useful in technical applications such as cluster analysis, speech and object recognition, or information retrieval in large databases [14], [15], [16], [17], [18], [19], [20], [21].…”

Section: Introductionmentioning

confidence: 99%

Optimal synaptic learning in non-linear associative memory

Knoblauch

2010

The 2010 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

Neural associative memories are single layer perceptrons with fast synaptic learning typically storing discrete associations between pairs of neural activity patterns. For linear learning such as employed in Hopfield-type networks it is well known that the so-called covariance rule is optimal resulting in minimal output noise and maximal storage capacity. On the other hand, numerical simulations suggest that nonlinear rules such as clipped Hebbian learning in Willshaw-type networks perform better, at least for sparse neural activity and finite network size. Here I show that the Willshaw and Hopfield models are only limit cases of a general optimal model where synaptic learning is determined by probabilistic Bayesian considerations. Asymptotically, for large networks and very sparse neuron activity the Bayesian model becomes identical to an inhibitory implementation of the Willshaw model. Similarly, for less sparse patterns, the Bayesian model becomes identical to the Hopfield network employing the covariance rule. For intermediate sparseness or finite networks the optimal Bayesian rule differs from both the Willshaw and Hopfield models and can significantly improve memory performance.

show abstract

“…The system described by Bentz et al [7] stores words as ASCII patterns. In that way, a misspelled word or a word not in the collection can retrieve a similar word.…”

Section: Associative Memoriesmentioning

confidence: 99%

Tolerant Information Retrieval with Backpropagation Networks

Mandl

2000

Neural Computing & Applications

View full text Add to dashboard Cite

Neural networks can learn from human decisions and preferences. Especially in human-computer interaction, adaptation to the behaviour and expectations of the user is necessary. In information retrieval, an important area within human-computer interaction, expectations are difficult to meet. The inherently vague nature of information retrieval has led to the application of vague processing techniques. Neural networks seem to have great potential to model the cognitive processes involved more appropriately. Current models based on neural networks and their implications for human-computer interaction are analysed. COSIMIR (Cognitive Similarity Learning in Information Retrieval), an innovative model integrating human knowledge into the core of the retrieval process, is presented. It applies backpropagation to information retrieval, integrating human-centred and soft and tolerant computing into the core of the retrieval process. A further backpropagation model, the transformation network for heterogeneous data sources, is discussed. Empirical evaluations have provided promising results. Information RetrievalInformation retrieval deals with the storage and representation of knowledge and the retrieval of relevant information. The user or information seeker Correspondence and offprint requests to:

show abstract

Information storage and effective data retrieval in sparse matrices

Cited by 32 publications

References 3 publications

A functional hypothesis for adult hippocampal neurogenesis: Avoidance of catastrophic interference in the dentate gyrus

A functional hypothesis for adult hippocampal neurogenesis: Avoidance of catastrophic interference in the dentate gyrus

Optimal synaptic learning in non-linear associative memory

Tolerant Information Retrieval with Backpropagation Networks

Contact Info

Product

Resources

About