Dynamic tunneling technique for efficient training of multilayer perceptrons
- 1 January 1999
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks
- Vol. 10 (1), 48-55
- https://doi.org/10.1109/72.737492
Abstract
A new efficient computational technique for training of multilayer feedforward neural networks is proposed. The proposed algorithm consists two learning phases. The first phase is a local search which implements gradient descent, and the second phase is a direct search scheme which implements dynamic tunneling in weight space avoiding the local trap thereby generates the point of next descent. The repeated application of these two phases alternately forms a new training procedure which results into a global minimum point from any arbitrary initial choice in the weight space. The simulation results are provided for five test examples to demonstrate the efficiency of the proposed method which overcomes the problem of initialization and local minimum point in multilayer perceptrons.Keywords
This publication has 14 references indexed in Scilit:
- TRUST: A Deterministic Algorithm for Global OptimizationScience, 1997
- Efficient Backpropagation Learning Using Optimal Learning Rate and MomentumNeural Networks, 1997
- Effective Backpropagation Training with Variable StepsizeNeural Networks, 1997
- Fast Second Order Learning Algorithm for Feedforward Multilayer Neural Networks and its ApplicationsNeural Networks, 1996
- A generalized learning paradigm exploiting the structure of feedforward neural networksIEEE Transactions on Neural Networks, 1996
- A fast multilayer neural-network training algorithm based on the layer-by-layer optimizing proceduresIEEE Transactions on Neural Networks, 1996
- Advances in feedforward neural networks: demystifying knowledge acquiring black boxesIEEE Transactions on Knowledge and Data Engineering, 1996
- Terminal repeller unconstrained subenergy tunneling (trust) for fast global optimizationJournal of Optimization Theory and Applications, 1993
- First- and Second-Order Methods for Learning: Between Steepest Descent and Newton's MethodNeural Computation, 1992
- The Science of ProgrammingPublished by Springer Nature ,1981