Title :
A new neuron model for additional learning
Author :
Fukuda, Toshio ; Shiotani, Shigetoshi ; Arai, Fumihito
Author_Institution :
Dept. of Mech. Eng., Nagoya Univ., Japan
Abstract :
A novel neuron model called the new neural network (NNN) is proposed. It is shown that the NNN can learn and memorize additionally and recognize unlearned patterns by its generalization for two simulations on recognition. The NNN can recognize unlearned patterns more efficiently than backpropagation by the evaluation function in which the similarity is considered. The NNN has two excellent abilities: additional learning and superior generalization
Keywords :
learning (artificial intelligence); neural nets; pattern recognition; NNN; additional learning; backpropagation; neuron model; new neural network; unlearned patterns; Cities and towns; Humans; Image recognition; Mechanical engineering; Neural networks; Neurons; Pattern matching; Pattern recognition; Resonance; Subspace constraints;
Conference_Titel :
Neural Networks, 1992. IJCNN., International Joint Conference on
Conference_Location :
Baltimore, MD
Print_ISBN :
0-7803-0559-0
DOI :
10.1109/IJCNN.1992.287066
