Title :
Mutual information neuro-evolutionary system (MINES)
Author :
Smith, Robert E. ; Behzadan, Behzad
Author_Institution :
Dept. of Comput. Sci., Univ. Coll. London, London
Abstract :
This article presents a new approach for automatically determining the optimal quantity and connectivity of the hidden-layer of a three-layer Feed-Forward Neural Network (FFNN) based on a theoretical and practical approach. The system (MINES) is a combination of Neural Network (NN), Back-Propagation (BP), Genetic Algorithm (GA), Mutual Information (MI), and clustering. BP is used to reduce the training-error while MI aides BP to follow an effective path. A GA changes the incoming synaptic connections of the hidden-nodes based on MI fitness. Assigning MI as the fitness of individuals brings a competition between hidden-nodes to acquire a higher amount of information from the error-space. Weight clustering is applied to reduce those hidden-nodes having similar weights. Experimental results are presented, and future directions discussed.
Keywords :
backpropagation; feedforward neural nets; genetic algorithms; pattern clustering; backpropagation; feedforward neural network; genetic algorithm; mutual information neuroevolutionary system; weight clustering; Error correction; Feedforward neural networks; Feedforward systems; Genetic algorithms; Mutual information; Neural networks; Propagation delay; Random variables; Search problems;
Conference_Titel :
Evolutionary Computation, 2009. CEC '09. IEEE Congress on
Conference_Location :
Trondheim
Print_ISBN :
978-1-4244-2958-5
Electronic_ISBN :
978-1-4244-2959-2
DOI :
10.1109/CEC.2009.4983123
