A Lamarckian Approach for Neural Network Training

Authors:
Paulo Cortez;Miguel Rocha;José Neves
Affiliations:
Departamento de Informática, Campus de Gualtar, Universidade do Minho, 4710-057 Braga, Portugal. E-mail: pcortez@di.uminho.pt;Departamento de Informática, Campus de Gualtar, Universidade do Minho, 4710-057 Braga, Portugal. E-mail: mrocha@di.uminho.pt;Departamento de Informática, Campus de Gualtar, Universidade do Minho, 4710-057 Braga, Portugal. E-mail: jneves@di.uminho.pt
Venue:
Neural Processing Letters
Year:
2002

Citing 7
Cited 6

Learning internal representations by error propagation

Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
Efficient genetic algorithms for training layered feedforward neural networks

Information Sciences—Informatics and Computer Science: An International Journal
A quantitative study of experimental evaluations of neural network learning algorithms: current research practice

Neural Networks
Numerical Optimization of Computer Models

Numerical Optimization of Computer Models
Pattern Recognition and Neural Networks

Pattern Recognition and Neural Networks
Unifying Learning with Evolution Through Baldwinian Evolution and Lamarckism

Advances in Computational Intelligence and Learning: Methods and Applications
A study of the Lamarckian evolution of recurrent neural networks

IEEE Transactions on Evolutionary Computation

Evolution of neural networks for classification and regression

Neurocomputing
Social Organization of Evolving Multiple Classifier System Functioning in Changing Environments

ICANNGA '07 Proceedings of the 8th international conference on Adaptive and Natural Computing Algorithms, Part I
The influence of learning on evolution: A mathematical framework

Artificial Life
A Lamarckian Hybrid of Differential Evolution and Conjugate Gradients for Neural Network Training

Neural Processing Letters
An analysis of Lamarckian learning in changing environments

ECAL'09 Proceedings of the 10th European conference on Advances in artificial life: Darwin meets von Neumann - Volume Part II
Simultaneous evolution of neural network topologies and weights for classification and regression

IWANN'05 Proceedings of the 8th international conference on Artificial Neural Networks: computational Intelligence and Bioinspired Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

In Nature, living beings improve their adaptation to surrounding environments by means of two main orthogonal processes: evolution and lifetime learning. Within the Artificial Intelligence arena, both mechanisms inspired the development of non-orthodox problem solving tools, namely: Genetic and Evolutionary Algorithms (GEAs) and Artificial Neural Networks (ANNs). In the past, several gradient-based methods have been developed for ANN training, with considerable success. However, in some situations, these may lead to local minima in the error surface. Under this scenario, the combination of evolution and learning techniques may induce better results, desirably reaching global optima. Comparative tests that were carried out with classification and regression tasks, attest this claim.