Title :
The converging unlearning algorithm for the Hopfield neural network: optimal strategy
Author_Institution :
Inst. of Phys. & Technol., Moscow, Russia
Abstract :
The iterative unlearning algorithm converging to the projector (pseudo inverse) rule matrix is studied in the thermodynamical limit. The system of equations describing the spectral evolution of the iterated synaptic matrix is derived. Time-dependent unlearning strength optimizing the convergence of the algorithm is found, the convergence rate being explicitly calculated
Keywords :
Hopfield neural nets; Hopfield neural network; convergence; iterated synaptic matrix; iterative unlearning algorithm; projector rule matrix; spectral evolution; thermodynamical limit; Computer aided analysis; Convergence; Equations; Green function; Hopfield neural networks; Iterative algorithms; Physics;
Conference_Titel :
Pattern Recognition, 1994. Vol. 2 - Conference B: Computer Vision & Image Processing., Proceedings of the 12th IAPR International. Conference on
Conference_Location :
Jerusalem
Print_ISBN :
0-8186-6270-0
DOI :
10.1109/ICPR.1994.576884
