Title :
Multiplier-free feedforward networks
fDate :
6/24/1905 12:00:00 AM
Abstract :
A feedforward network is proposed which lends itself to cost-effective implementations in digital hardware and has a fast forward-pass capability. It differs from the conventional model in restricting its synapses to the set {-1, 0, 1} while allowing unrestricted offsets. Simulation results on the ´onset of diabetes´ data set and a handwritten numeral recognition database indicate that the new network, despite having strong constraints on its synapses, has a generalization performance similar to that of its conventional counterpart
Keywords :
feedforward neural nets; diabetes; digital hardware; fast forward-pass capability; feedforward neural network; generalization; handwritten numeral recognition database; multiplier-free feedforward networks; synapses; unrestricted offsets; Arithmetic; Computer architecture; Equations; Hardware; Machine learning; Neurons; Spatial databases; Very large scale integration;
Conference_Titel :
Neural Networks, 2002. IJCNN '02. Proceedings of the 2002 International Joint Conference on
Conference_Location :
Honolulu, HI
Print_ISBN :
0-7803-7278-6
DOI :
10.1109/IJCNN.2002.1007573
