Title :
Capacity of recurrent networks
Author_Institution :
Dept. of Maths., Univ. of Southern California, Los Angeles, CA, USA
Abstract :
It is shown that one can assign n arbitrarily linearly independent target outputs as fixed points for a recurrent network and that this assignment is independent of the dynamics of the system. The recurrent network has a capacity of at least n, which is the size of the net. The numerical complexity for obtaining the weights is discussed
Keywords :
computational complexity; matrix algebra; neural nets; capacity; dynamics; neural nets; numerical complexity; recurrent networks; weight matrix; Biological system modeling; Cells (biology); Chaos; Continuous time systems; Differential equations; Mathematical model; Mathematics; Neural networks; Neurons; Nonlinear dynamical systems;
Conference_Titel :
Neural Networks, 1991. 1991 IEEE International Joint Conference on
Print_ISBN :
0-7803-0227-3
DOI :
10.1109/IJCNN.1991.170581
