Title :
Use of a structured problem domain to explore development of modularized neural networks
Author :
Lendaris, George G. ; Todd, David N.
Author_Institution :
Portland State Univ., OR, USA
Abstract :
A technique has been devised and tested which allows separate training of neural network (NN) modules, each operating on a portion of the problem domain. A method for linking together the NN modules has been devised and shown to yield successful operation on the full problem domain. Methods in the graph theory literature known as connection matrix and reachability matrix were used to assist in both (i) decomposing the problem into subtasks and (ii) determining how to connect the NN modules that learn to perform the subtasks. The problem context used is a lattice of concept types underlying a knowledge base system
Keywords :
graph theory; knowledge based systems; neural nets; concept types; connection matrix; graph theory; knowledge base system; modularized neural networks; reachability matrix; structured problem domain; training; Graph theory; Joining processes; Knowledge based systems; Lattices; Matrix decomposition; Neural networks; Scalability; Testing; Training data;
Conference_Titel :
Neural Networks, 1992. IJCNN., International Joint Conference on
Conference_Location :
Baltimore, MD
Print_ISBN :
0-7803-0559-0
DOI :
10.1109/IJCNN.1992.227090
