Metaheuristic design of feedforward neural networks: A review of two decades of research

@article{Ojha2017MetaheuristicDO,
  title={Metaheuristic design of feedforward neural networks: A review of two decades of research},
  author={Varun Kumar Ojha and A. Abraham and V. Sn{\'a}{\vs}el},
  journal={ArXiv},
  year={2017},
  volume={abs/1705.05584}
}
Over the past two decades, the feedforward neural network (FNN) optimization has been a key interest among the researchers and practitioners of multiple disciplines. The FNN optimization is often viewed from the various perspectives: the optimization of weights, network architecture, activation nodes, learning parameters, learning environment, etc. Researchers adopted such different viewpoints mainly to improve the FNN's generalization ability. The gradient-descent algorithm such as… Expand
173 Citations
An Adaptive Multi-Population Optimization Algorithm for Global Continuous Optimization
  • PDF
Direct and Indirect Evolutionary Designs of Artificial Neural Networks
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 366 REFERENCES
Hybrid Multiobjective Evolutionary Design for Artificial Neural Networks
  • 92
Simultaneous optimization of neural network weights and active nodes using metaheuristics
  • 5
  • PDF
Speeding Up Backpropagation Using Multiobjective Evolutionary Algorithms
  • H. Abbass
  • Computer Science, Medicine
  • Neural Computation
  • 2003
  • 152
Neural network regularization and ensembling using multi-objective evolutionary algorithms
  • Y. Jin, T. Okabe, B. Sendhoff
  • Computer Science
  • Proceedings of the 2004 Congress on Evolutionary Computation (IEEE Cat. No.04TH8753)
  • 2004
  • 140
  • PDF
Training Neural Networks Using Multiobjective Particle Swarm Optimization
  • 15
  • PDF
Training neural networks using Central Force Optimization and Particle Swarm Optimization: Insights and comparisons
  • 54
...
1
2
3
4
5
...