Title :
Randomly connected neural nets
Author :
Dodd, R.K. ; Kirchherr, W.
Author_Institution :
Dept. of Math. & Comput. Sci., San Jose Univ., CA, USA
Abstract :
Summary form only given, as follows. Theories of efficient circuits which have a direct relevance for neural nets of arbitrary architecture are discussed. The main results are concerned with randomly connected neural nets which have a large number of nodes. These nets can be compared with those for the Hopfield model by taking the limit of a complete graph
Keywords :
graph theory; neural nets; Hopfield model; architecture; efficient circuits; graph theory; nodes; randomly connected neural nets; Circuits; Computer architecture; Computer science; Concrete; Informatics; Information analysis; Mathematics; Neural network hardware; Neural networks; Software tools;
Conference_Titel :
Neural Networks, 1991., IJCNN-91-Seattle International Joint Conference on
Conference_Location :
Seattle, WA
Print_ISBN :
0-7803-0164-1
DOI :
10.1109/IJCNN.1991.155662
