Τίτλος:
Development and convergence analysis of training algorithms with local
learning rate adaptation
Γλώσσες Τεκμηρίου:
Αγγλικά
Περίληψη:
A new theorem for the development and convergence analysis of supervised
training algorithms with an adaptive learning rate for each weight is
presented. Based on this theoretical result, a strategy is proposed to
automatically adapt the search direction, as well as the stepsize length
along the resultant search direction. This strategy is applied to some
well known local learning algorithms to investigate its effectiveness.
Συγγραφείς:
Magoulas, GD
Plagianakos, VP
Vrahatis, MN
Εκδότης:
IEEE Comput. Soc
Τίτλος συνεδρίου:
IJCNN 2000: PROCEEDINGS OF THE IEEE-INNS-ENNS INTERNATIONAL JOINT
CONFERENCE ON NEURAL NETWORKS, VOL I
Λέξεις-κλειδιά:
globally convergent algorithms; local learning rate adaptation; batch
training algorithms; gradient descent; feedforward neural networks
DOI:
10.1109/IJCNN.2000.857808
