Title :
Supervised learning with artificial selection
Author :
Hagiwara, Manabu ; Nakagawa, Masaki
Author_Institution :
Fac. of Sci. & Technol., Keio Univ., Yokohama, Japan
Abstract :
Summary form only given, as follows. Supervised learning with artificial selection is proposed as a way to escape from local minima. The concept of artificial selection is reasonable for nature. In the authors´ method, the ´worst´ hidden unit is detected, and then all the weights connected to the detected hidden unit are reset to small random values. According to simulations, only half the trials using conventional backpropagation converge, whereas all of the trials using the proposed method converge, and quickly do so.<>
Keywords :
convergence of numerical methods; digital simulation; learning systems; neural nets; backpropagation; convergence; escape from local minima; simulations; supervised learning with artificial selections; Convergence of numerical methods; Learning systems; Neural networks; Simulation;
Conference_Titel :
Neural Networks, 1989. IJCNN., International Joint Conference on
Conference_Location :
Washington, DC, USA
DOI :
10.1109/IJCNN.1989.118443
