Filters








10 Hits in 1.4 sec

Thresholded Learning Matrix for Efficient Pattern Recalling [chapter]

Mario Aldape-Pérez, Israel Román-Godínez, Oscar Camacho-Nieto
2008 Lecture Notes in Computer Science  
The algorithm applies the dynamic threshold value over the ambiguously recalled class vector in order to obtain a sentinel vector which is used for uncertainty elimination purposes.  ...  The crossbars saturation occurrence is solved by means of a dynamic threshold value which is computed for each recalled pattern.  ...  The authors of the present paper would like to thank the following institutions for their economical support to develop this work: National Polytechnic Institute, Mexico (CIC, SIP, PIFI, COFAA) , CONACyT  ... 
doi:10.1007/978-3-540-85920-8_55 fatcat:v76a2p5mqvc2te7kx4i2r3qvta

A Novel and Simple Mathematical Transform Improves the Perfomance of Lernmatrix in Pattern Classification

José-Luis Velázquez-Rodríguez, Yenny Villuendas-Rey, Oscar Camacho-Nieto, Cornelio Yáñez-Márquez
2020 Mathematics  
The Lernmatrix is a classic associative memory model.  ...  The Lernmatrix is capable of executing the pattern classification task, but its performance is not competitive when compared to state-of-the-art classifiers.  ...  Acknowledgments: The authors want to thank the Instituto Politécnico Nacional of Mexico (Secretaría Académica, CIC, SIP and CIDETEC), the CONACyT, and SNI for their support to develop this work.  ... 
doi:10.3390/math8050732 fatcat:uxshbufhxfdz7biobxxcre2hna

Financial distress prediction using the hybrid associative memory with translation

L. Cleofas-Sánchez, V. García, A.I. Marqués, J.S. Sánchez
2016 Applied Soft Computing  
The method is based on a type of neural network, which is called hybrid associative memory with translation.  ...  better than the rest of models under class imbalance and data overlapping conditions in terms of the true positive rate and the geometric mean of true positive and true negative rates.  ...  We would like to thank the Reviewers for their valuable comments and suggestions, which have helped to improve the quality of this paper substantially.  ... 
doi:10.1016/j.asoc.2016.04.005 fatcat:f622tuzyqjgobbxwcsqrrhom3u

Morphological Associative Memories for Gray-Scale Image Encryption

Mar�a Elena Acevedo, Jos� �ngel Mart�nez, Marco Antonio Acevedo, Cornelio Ya�ez
2014 Applied Mathematics & Information Sciences  
The image is divided in blocks which are used to build max and min Morphological associative memories. The key is private and it depends on the number of blocks.  ...  The main advantage of this method is that the cyphertext does not have the same size than the original image; therefore, since the beginning the adversary cannot know what the image means.  ...  One by one, each input vector x i is operated with the associative memories M and W by using equations (7) and (8) and the output vector y i is recalled.  ... 
doi:10.12785/amis/080115 fatcat:zxmbv5rhsfef3brb475qojfepa

A Fast Search Algorithm for Vector Quantization Based on Associative Memories [chapter]

Enrique Guzmán, Oleksiy Pogrebnyak, Luis Sánchez Fernández, Cornelio Yáñez-Márquez
2008 Lecture Notes in Computer Science  
This associative network is EAM-codebook which is used by the FSA-EAM. The FSA-EAM VQ process is performed using the recalling stage of EAM.  ...  One of the most serious problems in vector quantization is the high computational complexity at the encoding phase.  ...  The EAM-codebook is based on the EAM training stage and the VQ process is performed using the EAM recalling stage.  ... 
doi:10.1007/978-3-540-85920-8_60 fatcat:weqgjsa5gbgzhnvyfw7grbg2we

A study of pattern recovery in recurrent correlation associative memories

R.C. Wilson, E.R. Hancock
2003 IEEE Transactions on Neural Networks  
Our second contribution is to develop an expression for the expectation value of bit-error probability on the input pattern after one iteration.  ...  It also alllows us to develop an expression for the storage capacity for a given recall error rate.  ...  Second, the restrictions on the properties of the input patterns quite limiting. In fact, in these cases, choosing the closest pattern would result in perfect recall.  ... 
doi:10.1109/tnn.2003.811559 pmid:18238035 fatcat:vxu5qpxi5fcvdlbygcmkobydlm

Applied Extended Associative Memories to High-Speed Search Algorithm for Image Quantization [chapter]

Enrique Guzman, Miguel A., Oleksiy Pogrebnyak
2011 Search Algorithms and Applications  
The proposed fuzzy LVQ uses the different learning rate depending on whether classification is correct or not.  ...  On the other hand, when the classification is not correct, it uses the combination of the fuzzy membership value and a function of the number of iteration as the fuzzy learning rate.  ...  In encoding phase, we propose a High-Speed Search Algorithm Applied to Image Quantization based on EAM; the VQ process is performed by means of the recalling stage of EAM using as associative memory the  ... 
doi:10.5772/14246 fatcat:ef6kwjs5zna43cxesnzuem7zny

Two coding strategies for bidirectional associative memory

Y.-F. Wang, J.B. Cruz, J.H. Mulligan
1990 IEEE Transactions on Neural Networks  
We derive a combinatorial formula with a highly reduced evaluation time that is used in the improved error analysis of the basic model and for estimation of the retrieval error in the naive model extension  ...  The distribution of the dendritic sum in the finite Willshaw model given by Buckingham and Willshaw [Buckingham, J., & Willshaw, D. (1992) . Performance characteristics of associative nets.  ...  Acknowledgements The authors would like to thank N. Palomero-Gallagher and T. Wennekers for their comments and suggestions which helped in improving the manuscript.  ... 
doi:10.1109/72.80207 pmid:18282825 fatcat:qiwq7jaldzdbdfawqcb3lcou6q

Improved bidirectional retrieval of sparse patterns stored by Hebbian learning

Friedrich T. Sommer, Günther Palm
1999 Neural Networks  
We derive a combinatorial formula with a highly reduced evaluation time that is used in the improved error analysis of the basic model and for estimation of the retrieval error in the naive model extension  ...  The distribution of the dendritic sum in the finite Willshaw model given by Buckingham and Willshaw [Buckingham, J., & Willshaw, D. (1992) . Performance characteristics of associative nets.  ...  Acknowledgements The authors would like to thank N. Palomero-Gallagher and T. Wennekers for their comments and suggestions which helped in improving the manuscript.  ... 
doi:10.1016/s0893-6080(98)00125-7 pmid:12662704 fatcat:jurcf5kxrfenfpp24jcynzsxoq

LookIT. LookKIT. Das Magazin für Forschung, Lehre, Innovation. The magazine for research, teaching, innovation. 2014,4 [article]

Karlsruher Institut Für Technologie (KIT). Karlsruhe Institute Of Technology
2014
studEnts Working as microsof t it supportErs ErkEnnung: protot yp nursEEyE mEldE t stür zE rEcognition: nursEE yE protot ypE rEports falls EnErgiEWEndE: EnErgy l ab 2.0 gEstartE t EnErgiEWEndE: start of thE  ...  Recalling the start of the journey when flying to Ger-many, it was full of twists and turns.  ...  DISCOUNT on our entire product portfolio! Do you have technical questions? Do you have technical questions? Edmund Optics® -your Perfect Partner!  ... 
doi:10.5445/ir/1000044910 fatcat:cdoacpuzobgo7awtqxy6ywp22q