Global descent replaces gradient descent to avoid local minima problem in learning with artificial neural networks

IEEE International Conference on Neural Networks - Conference Proceedings

Volumn 1993-January, Issue , 1993, Pages 836-842

  Cetin, Bedri C ^a   Burdick, Joel W ^a   Barhen, Jacob ^a  

^a CALIFORNIA INSTITUTE OF TECHNOLOGY   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

BACKPROPAGATION; BACKPROPAGATION ALGORITHMS; DYNAMICAL SYSTEMS; GLOBAL OPTIMIZATION; NEURAL NETWORKS; OPTIMIZATION; PATTERN RECOGNITION; PATTERN RECOGNITION SYSTEMS;

BACKPROPAGATION LEARNING ALGORITHM; DETERMINISTIC DYNAMICAL SYSTEMS; FUNDAMENTAL LIMITATIONS; GRADIENT DESCENT; LOCAL MINIMA PROBLEMS; LOCAL MINIMUMS; NEW APPROACHES; SPECIFIC PROBLEMS;

LEARNING ALGORITHMS;

EID: 84943257899     PISSN: 10987576     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICNN.1993.298667     Document Type: Conference Paper

References (0)