Evolutional development of a multilevel neural network

Odri, S.; Petrovački, Dušan; Krstonosic, Gordana A.

doi:10.1016/s0893-6080(05)80061-9

Cited by 48 publications

(24 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Regarding the new neuron that will be added, we follow the the biological process of 'cell division' (Odri et al, 1993). By this way the neuron with the highest quantization error is 'splitted' to two new neurons (instead of just adding one new neuron somewhere at random with no connections at all).…”

Section: Adding and Removing Neuronsmentioning

confidence: 99%

“…where w u refers to the weight vector of neuron u (neuron that is splitted) and β is a mutation parameter which can take either a fixed or random value according to a certain distribution rule (following (Odri et al, 1993)). In any case, value of β has to be chosen small in order to avoid a large change both in network topology but also in the weight vectors.…”

Section: Adding and Removing Neuronsmentioning

confidence: 99%

See 1 more Smart Citation

AMSOM: Adaptive Moving Self-organizing Map for Clustering and Visualization

Spanakis¹,

Weiß

2016

Proceedings of the 8th International Conference on Agents and Artificial Intelligence

View full text Add to dashboard Cite

Abstract:Self-Organizing Map (SOM) is a neural network model which is used to obtain a topology-preserving mapping from the (usually high dimensional) input/feature space to an output/map space of fewer dimensions (usually two or three in order to facilitate visualization). Neurons in the output space are connected with each other but this structure remains fixed throughout training and learning is achieved through the updating of neuron reference vectors in feature space. Despite the fact that growing variants of SOM overcome the fixed structure limitation they increase computational cost and also do not allow the removal of a neuron after its introduction. In this paper, a variant of SOM is proposed called AMSOM (Adaptive Moving Self-Organizing Map) that on the one hand creates a more flexible structure where neuron positions are dynamically altered during training and on the other hand tackles the drawback of having a predefined grid by allowing neuron addition and/or removal during training. Experiments using multiple literature datasets show that the proposed method improves training performance of SOM, leads to a better visualization of the input dataset and provides a framework for determining the optimal number and structure of neurons.

show abstract

Section: Adding and Removing Neuronsmentioning

confidence: 99%

Section: Adding and Removing Neuronsmentioning

confidence: 99%

AMSOM: Adaptive Moving Self-organizing Map for Clustering and Visualization

Spanakis¹,

Weiß

2016

Proceedings of the 8th International Conference on Agents and Artificial Intelligence

View full text Add to dashboard Cite

show abstract

“…The process of a node splitting is called "cell division" by Odri et al [39]. Two nodes created by splitting an existing node have the same number of connections as the existing node.…”

Section: Architecture Modificationsmentioning

confidence: 99%

A constructive algorithm for training cooperative neural network ensembles

Islam

Yao

Murase

2003

IEEE Trans. Neural Netw.

266

126

View full text Add to dashboard Cite

Abstract-This paper presents a constructive algorithm for training cooperative neural-network ensembles (CNNEs). CNNE combines ensemble architecture design with cooperative training for individual neural networks (NNs) in ensembles. Unlike most previous studies on training ensembles, CNNE puts emphasis on both accuracy and diversity among individual NNs in an ensemble. In order to maintain accuracy among individual NNs, the number of hidden nodes in individual NNs are also determined by a constructive approach. Incremental training based on negative correlation is used in CNNE to train individual NNs for different numbers of training epochs. The use of negative correlation learning and different training epochs for training individual NNs reflect CNNEs emphasis on diversity among individual NNs in an ensemble. CNNE has been tested extensively on a number of benchmark problems in machine learning and neural networks, including Australian credit card assessment, breast cancer, diabetes, glass, heart disease, letter recognition, soybean, and Mackey-Glass time series prediction problems. The experimental results show that CNNE can produce NN ensembles with good generalization ability.

show abstract

“…There have been many applications for parametric learning [24] and for both parametric and structural learning [8], [17], [25]- [32]. These works fall in two broad categories of evolutionary computation: genetic algorithms and evolutionary programming.…”

Section: Automatic Design Of Artificial Neural Networkmentioning

confidence: 99%

“…However, a lot of work has been made in these two decades, leaving many different approaches and working models, for instance, [8], [25], or [30]. Evolutionary computation has been used for learning connection weights and for learning both architecture and connection weights.…”

Section: Automatic Design Of Artificial Neural Networkmentioning

confidence: 99%

COVNET: a cooperative coevolutionary model for evolving artificial neural networks

García-Pedrajas

Hervás-Martı́nez

Pérez

2003

IEEE Trans. Neural Netw.

191

View full text Add to dashboard Cite

Abstract-This paper presents COVNET, a new cooperative coevolutionary model for evolving artificial neural networks. This model is based on the idea of coevolving subnetworks that must cooperate to form a solution for a specific problem, instead of evolving complete networks. The combination of this subnetworks is part of a coevolutionary process. The best combinations of subnetworks must be evolved together with the coevolution of the subnetworks. Several subpopulations of subnetworks coevolve cooperatively and genetically isolated. The individual of every subpopulation are combined to form whole networks. This is a different approach from most current models of evolutionary neural networks which try to develop whole networks. COVNET places as few restrictions as possible over the network structure, allowing the model to reach a wide variety of architectures during the evolution and to be easily extensible to other kind of neural networks. The performance of the model in solving three real problems of classification is compared with a modular network, the adaptive mixture of experts and with the results presented in the bibliography. COVNET has shown better generalization and produced smaller networks than the adaptive mixture of experts and has also achieved results, at least, comparable with the results in the bibliography.

show abstract

Evolutional development of a multilevel neural network

Cited by 48 publications

References 2 publications

AMSOM: Adaptive Moving Self-organizing Map for Clustering and Visualization

AMSOM: Adaptive Moving Self-organizing Map for Clustering and Visualization

A constructive algorithm for training cooperative neural network ensembles

COVNET: a cooperative coevolutionary model for evolving artificial neural networks

Contact Info

Product

Resources

About