Title :
A recurrent dynamic network for associative recall
Author :
Hou, Jiansheng ; Salam, Fathi M A
Author_Institution :
Dept. of Electr. Eng., Michigan State Univ., East Lansing, MI, USA
Abstract :
A model for recurrent artificial neural networks which can store any number of any prespecified patterns as energy local minima is presented. Therefore, all the prespecified patterns can be stored and recalled. Some examples are given to show how this model can be used in image recognition and association. Generalization of the energy function is discussed. Variations of this model are also investigated for performance improvement and potential hardware implementation
Keywords :
image recognition; recurrent neural nets; associative recall; dynamic network; energy function; energy local minima; image recognition; recurrent artificial neural networks; Artificial neural networks; Circuits; Computer networks; Electronic mail; Equations; Laboratories; Mathematical model; Neural network hardware; Neural networks; Neurons;
Conference_Titel :
Systems Engineering, 1992., IEEE International Conference on
Conference_Location :
Kobe
Print_ISBN :
0-7803-0734-8
DOI :
10.1109/ICSYSE.1992.236950
