A New Adaptive Merging and Growing Algorithm for Designing Artificial Neural Networks

By M. Islam, Md. Abdus Sattar, Md. Faijul Amin, Xin Yao, Kazuyuki Murase. 2009

129 citations recorded by the source corpus.

This paper presents a new algorithm, called adaptive merging and growing algorithm (AMGA), in designing artificial neural networks (ANNs). This algorithm merges and adds hidden neurons during the training process of ANNs. The merge operation introduced in AMGA is a kind of a mixed mode operation, which is equivalent to pruning two neurons and adding one neuron. Unlike most previous studies, AMGA puts emphasis on autonomous functioning in the design process of ANNs. This is the main reason why AMGA uses an adaptive not a predefined fixed strategy in designing ANNs. The adaptive strategy merges or adds hidden neurons based on the learning ability of hidden neurons or the training progress of ANNs. In order to reduce the amount of retraining after modifying ANN architectures, AMGA prunes hidden neurons by merging correlated hidden neurons and adds hidden neurons by splitting existing hidden neurons. The proposed AMGA has been tested on a number of benchmark problems in machine learning and ANNs, including breast cancer, Australian credit card assessment, and diabetes, gene, glass, heart, iris, and thyroid problems. The experimental results show that AMGA can design compact ANN architectures with good generalization ability compared to other algorithms.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

AdaNet: Adaptive Structural Learning of Artificial Neural Networks (2016, background): “L G ] 5 J u l 2016 3. adapts the structure and complexity of the network to the difﬁculty of the particular problem at hand, with no pre-deﬁned architecture.”
A structure optimisation algorithm for feedforward neural network construction (2013, methodology): “The results are compared with the EFAST FNN [17], AGPNNC [20], the AMGA [23], the MPANN-HN [33], and the EI-ELM [11] algorithms.”