loading...
 This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
18th IEEE International Conference on Tools with Artificial Intelligence (ICTAI'06)
Exponential Recurrent Associative Memories: Stability and Relative Capacity
Arlington, Virginia
November 13-November 15
ISBN: 0-7695-2728-0
ASCII Text
x 
 
Mohammad Reza Rajati, Mohammad Bagher Menhaj, Mohammad Mehdi Korjani, Alireza Dehestani, "Exponential Recurrent Associative Memories: Stability and Relative Capacity," Tools with Artificial Intelligence, IEEE International Conference on, pp. 751-755, 18th IEEE International Conference on Tools with Artificial Intelligence (ICTAI'06), 2006.
 
 
BibTex
x
 
@article{ 10.1109/ICTAI.2006.58,
author = {Mohammad Reza Rajati and Mohammad Bagher Menhaj and Mohammad Mehdi Korjani and Alireza Dehestani},
title = {Exponential Recurrent Associative Memories: Stability and Relative Capacity},
journal ={Tools with Artificial Intelligence, IEEE International Conference on},
volume = {0},
year = {2006},
issn = {1082-3409},
pages = {751-755},
doi = {http://doi.ieeecomputersociety.org/10.1109/ICTAI.2006.58},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
}
 
 
RefWorks Procite/RefMan/Endnote
x 
 
TY - CONF
JO - Tools with Artificial Intelligence, IEEE International Conference on
TI - Exponential Recurrent Associative Memories: Stability and Relative Capacity
SN - 1082-3409
SP751
EP755
A1 - Mohammad Reza Rajati,
A1 - Mohammad Bagher Menhaj,
A1 - Mohammad Mehdi Korjani,
A1 - Alireza Dehestani,
PY - 2006
KW - null
VL - 0
JA - Tools with Artificial Intelligence, IEEE International Conference on
ER -
 
Mohammad Reza Rajati, K.N. Toosi University of Technology, Iran
Mohammad Bagher Menhaj, Amirkabir University of Technology, Iran
Mohammad Mehdi Korjani, Amirkabir University of Technology, Iran
Alireza Dehestani, Iran Telecom Research Center, Iran
In this paper, relative capacity of a specific higher order Hopfield-type associative memory is considered. This model, which is known as exponential Hopfield Neural Network is suitable for hardware implementation and is not of a great computational cost. It is shown that, this modification of the Hopfield model significantly improves the storage capacity of the associative memory. We also classify the model via a stability measure, and study the effect of training the network with biased patterns on the stability.
Citation:
Mohammad Reza Rajati, Mohammad Bagher Menhaj, Mohammad Mehdi Korjani, Alireza Dehestani, "Exponential Recurrent Associative Memories: Stability and Relative Capacity," ictai, pp.751-755, 18th IEEE International Conference on Tools with Artificial Intelligence (ICTAI'06), 2006
Usage of this product signifies your acceptance of the Terms of Use.