On the alleviation of the problem of local minima in back-propagation

DOI10.1016/S0362-546X(96)00369-0zbMath0891.68089WikidataQ126350707 ScholiaQ126350707MaRDI QIDQ4378898

G. S. Androulakis, George D. Magoulas, Michael N. Vrahatis

Publication date: 19 July 1998

Published in: Nonlinear Analysis: Theory, Methods & Applications (Search for Journal in Brave)

zbMATH Keywords

backpropagationlocal minima in BP training

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Related Items (8)

Computation of multiple global optima through chaotic ant swarm ⋮ Nonmonotone BFGS-trained recurrent neural networks for temporal sequence processing ⋮ Reservoir computing for forecasting large spatiotemporal dynamical systems ⋮ An evolutionary game based particle swarm optimization algorithm ⋮ An efficient algorithm for global periodic orbits generation near irregular-shaped asteroids ⋮ Computing Nash equilibria through computational intelligence methods ⋮ Improved sign-based learning algorithm derived by the composite nonlinear Jacobi process ⋮ Inverse optimal control for linearizable nonlinear systems with input delays

Uses Software

• simannf90

Cites Work

• Optimization by Simulated Annealing
• simannf90
• Minimizing multimodal functions of continuous variables with the “simulated annealing” algorithm—Corrigenda for this article is available here
• Unnamed Item
• Unnamed Item

This page was built for publication: On the alleviation of the problem of local minima in back-propagation