High Performance Recording Algorithm For Hopfield Model Associative Memories

Hassoun, M.H.; Youssef, Abbas M.

doi:10.1117/12.7976900

Cited by 25 publications

(17 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The value corresponds to ; taking into account that there are 45 vectors at , the recall accuracy is 86% with the SVM and 58% with the perceptron. For sake of comparison we consider the results in [17], based on the Ho-Kashyap method [18]: They are % for and % for and . Example 2: Here, we consider a specific design example and compare four different design strategies: SVM standard, SVM with fixed threshold according to (23), perceptron, and the designer neural network of Chan and Zak.…”

Section: Resultsmentioning

confidence: 99%

“…We examined also the capacity measure proposed in [18], based on the concept of recall accuracy (RA) for a given Hamming radius .…”

Section: Resultsmentioning

confidence: 99%

“…Assume is a stable equilibrium point, and a random bipolar pattern with the constraint that it differs from in th component. Assuming , condition (14) can be rewritten as follows: (18) where are random variables with values 0, and . From th condition (13) Thus, we can write (20) where denotes the error function.…”

Section: In Thementioning

confidence: 99%

See 2 more Smart Citations

Associative Memory Design Using Support Vector Machines

Casali

Costantini

Perfetti

et al. 2006

IEEE Trans. Neural Netw.

View full text Add to dashboard Cite

The relation existing between support vector machines (SVMs) and recurrent associative memories is investigated. The design of associative memories based on the generalized brain-state-in-a-box (GBSB) neural model is formulated as a set of independent classification tasks which can be efficiently solved by standard software packages for SVM learning. Some properties of the networks designed in this way are evidenced, like the fact that surprisingly they follow a generalized Hebb's law. The performance of the SVM approach is compared to existing methods with nonsymmetric connections, by some design examples.

show abstract

Section: Resultsmentioning

confidence: 99%

“…We examined also the capacity measure proposed in [18], based on the concept of recall accuracy (RA) for a given Hamming radius .…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Associative Memory Design Using Support Vector Machines

Casali

Costantini

Perfetti

et al. 2006

IEEE Trans. Neural Netw.

View full text Add to dashboard Cite

show abstract

“…In this paper, we extend our earlier work on the Ho-Kashyap training procedure [7,8] and derive, based on gradient descent strategies, three new adaptive Ho-Kashyap (AHK) training rules: AHK I, AHK II, and AHK III. We propose these training rules as alternatives to LMS and perceptron training rules for classification problems.…”

Section: Introductionmentioning

confidence: 99%

<title>Adaptive versions of the Ho-Kashyap learning algorithm</title>

Hassoun

1991

SPIE Proceedings

View full text Add to dashboard Cite

ABsTRA::r Three adaptive versions of the Ho-Kashyap perceptron training algorithm are derived based on gradient descent strategies. These adaptive Ho-Kashyap (AHK) training rules are comparable in their complexity to the LMS and perceptron training rules and are capable of adaptively forming linear discriminant surfaces which guarantee linear separability, and positioning such surfaces for maximal classification robustness. In particular, a derived version called ARK II is capable of adaptively identifying critical input vectors lying close to class boundaries in linearly separable problems. We also extend this algorithm as AHK Ill which adds the capability of fast convergence to linear discriminant surfaces which are "good" approximations for nonlinearly separable problems.

show abstract

“…Other related work can be found in [16], [17], [18] and [19] in which either by adding dummy neuron, increasing in number of layers or manipulating the interconnection among neurons in each layer, the issue of performance improvement of BAM is addressed. Even some new learning algorithms were introduced to improve the performance of original BAM and can be found in detail in [20]- [24].…”

Section: Related Workmentioning

confidence: 99%