Associative Memory Design Using Support Vector Machines

Casali, Daniele; Costantini, Giovanni; Perfetti, R.; Ricci, Elisa

doi:10.1109/tnn.2006.877539

Cited by 22 publications

(9 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The experiment is conducted like Example 6 assuming and . The connection weights and thresholds of the network have been computed using two different techniques: the pseudoinverse method and the linear SVM illustrated in [4]. In the second Fig.…”

Section: B Polynomial Kernelmentioning

confidence: 99%

“…11. Comparison between the quadratic RKAM (R = 1) and a first-order Hopfield network designed using the pseudoinverse method and the linear SVM in [4] (N = 32; M = 16). RKAM: " ," PINV: "2," linear SVM: "3."…”

Section: B Polynomial Kernelmentioning

confidence: 99%

“…The capacity of the Hopfield network can be estimated as , where is the dimensionality of the stored vectors [3]. Using more sophisticated techniques to design the connection matrix, correlated patterns can be stored but the error correction is often unsatisfactory [4]- [7].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Recurrent Correlation Associative Memories: A Feature Space Perspective

Perfetti

Ricci

2008

IEEE Trans. Neural Netw.

Self Cite

View full text Add to dashboard Cite

In this paper, we analyze a model of recurrent kernel associative memory (RKAM) recently proposed by Garcia and Moreno. We show that this model consists in a kernelization of the recurrent correlation associative memory (RCAM) of Chiueh and Goodman. In particular, using an exponential kernel, we obtain a generalization of the well-known exponential correlation associative memory (ECAM), while using a polynomial kernel, we obtain a generalization of higher order Hopfield networks with Hebbian weights. We show that the RKAM can outperform the aforementioned associative memory models, becoming equivalent to them when a dominance condition is fulfilled by the kernel matrix. To ascertain the dominance condition, we propose a statistical measure which can be easily computed from the probability distribution of the interpattern Hamming distance or directly estimated from the memory vectors. The RKAM can be used below saturation to realize associative memories with reduced dynamic range with respect to the ECAM and with reduced number of synaptic coefficients with respect to higher order Hopfield networks.

show abstract

Section: B Polynomial Kernelmentioning

confidence: 99%

Section: B Polynomial Kernelmentioning

confidence: 99%

See 1 more Smart Citation

Recurrent Correlation Associative Memories: A Feature Space Perspective

Perfetti

Ricci

2008

IEEE Trans. Neural Netw.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Other schemes of associative memories based on recurrent neural networks, see for example [12,13], and other techniques [14][15][16][17][18] have been proposed.…”

Section: Introductionmentioning

confidence: 99%

A New Associative Model with Dynamical Synapses

Monteros¹,

Azuela²

2008

Neural Process Lett

View full text Add to dashboard Cite

The brain is not a huge fixed neural network, but a dynamic, changing neural network that continuously adapts to meet the demands of communication and computational needs. In classical neural networks approaches, particularly associative memory models, synapses are only adjusted during the training phase. After this phase, synapses are no longer adjusted. In this paper we describe a new dynamical model where synapses of the associative memory could be adjusted even after the training phase as a response to an input stimulus. We provide some propositions that guarantee perfect and robust recall of the fundamental set of associations. In addition, we describe the behavior of the proposed associative model under noisy versions of the patterns. At last, we present some experiments aimed to show the accuracy of the proposed model.

show abstract

“…Other schemes of associative memories based on recurrent neural networks (see for example [6,45]) and other techniques [7,30,33,54,55], have been proposed. Recently, morphological, median and fuzzy associative memories were proposed; refer for example to [9,35,40,52] and [44].…”

Section: Introductionmentioning

confidence: 99%

A Bidirectional Hetero-Associative Memory for True-Color Patterns

Monteros

Azuela

2008

Neural Process Lett

View full text Add to dashboard Cite

Classical bidirectional associative memories (BAM) have poor memory storage capacity, are sensitive to noise, are subject to spurious steady states during recall, and can only recall bipolar patterns. In this paper, we introduce a new bidirectional hetero-associative memory model for true-color patterns that uses the associative model with dynamical synapses recently introduced in Vazquez and Sossa (Neural Process Lett, Submitted, 2008). Synapses of the associative memory could be adjusted even after the training phase as a response to an input stimulus. Propositions that guarantee perfect and robust recall of the fundamental set of associations are provided. In addition, we describe the behavior of the proposed associative model under noisy versions of the patterns. At last, we present some experiments aimed to show the accuracy of the proposed model with a benchmark of truecolor patterns.

show abstract

Associative Memory Design Using Support Vector Machines

Cited by 22 publications

References 16 publications

Recurrent Correlation Associative Memories: A Feature Space Perspective

Recurrent Correlation Associative Memories: A Feature Space Perspective

A New Associative Model with Dynamical Synapses

A Bidirectional Hetero-Associative Memory for True-Color Patterns

Contact Info

Product

Resources

About