Title :
A two layer network using the OR/AND neuron
Author :
Bailey, Sean A. ; Chen, Ye-Hwa
Author_Institution :
Georgia Inst. of Technol., Atlanta, GA, USA
Abstract :
Revisits the concept of logical connectives in neural network-based form through the use of the OR/AND neuron. One layer implementations have been achieved previously. Here, the two layer learning rules are derived by hand and implemented using Matlab. Networks of varying hidden layer complexity are then used to model the kinematics of a 3 DOF robotic arm
Keywords :
learning (artificial intelligence); manipulator kinematics; multilayer perceptrons; neural net architecture; 3 DOF robotic arm; OR/AND neuron; hidden layer complexity; kinematics; logical connectives; neural network-based form; two layer learning rules; two layer network; Artificial neural networks; Backpropagation; Inspection; Kinematics; Logic; Mathematical model; Neural networks; Neurons; Robots; World Wide Web;
Conference_Titel :
Fuzzy Systems Proceedings, 1998. IEEE World Congress on Computational Intelligence., The 1998 IEEE International Conference on
Print_ISBN :
0-7803-4863-X
DOI :
10.1109/FUZZY.1998.686291
