Title :
A biologically-inspired improved MAXNET
Author :
Yadid-Pecht, Orly ; Gur, Moshe
Author_Institution :
Dept. of Biomed. Eng., Technion-Israel Inst. of Technol., Haifa, Israel
fDate :
5/1/1995 12:00:00 AM
Abstract :
A biologically-inspired modification to MAXNET is proposed. Unlike the original net where the weights are constant, the weights in the new net are dynamically changed. Consequently, the modified net achieves a drastic improvement in convergence rate. A simple hardware implementation for the modified net is presented
Keywords :
convergence; neural nets; optimisation; biologically-inspired improved MAXNET; convergence rate; maximum selection; neural net; Added delay; Binary trees; Biomedical engineering; Convergence; Hardware; Logic; Neural networks; Neurofeedback; Silver; Working environment noise;
Journal_Title :
Neural Networks, IEEE Transactions on
