Optimization of neural networks through grammatical evolution and a genetic algorithm

Campos, Lidio Mauro Lima de; Oliveira, Roberto Célio Limão de; Roisenberg, Mauro

doi:10.1016/j.eswa.2016.03.012

Cited by 40 publications

(14 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In this context, this paper test the possibilities of a hybrid system called Artificial Development and Evolution of Deep Neural Networks (ADEANN-Deep) for shor-term energy price prediction using explanatory variables. Our approach is inspired by two natural biological mechanisms: genetic encoding and the evolution of genetic coding [11].…”

Section: Introductionmentioning

confidence: 99%

“…In relation to the previous version of ADEANN [11], this research presents the following improvements: system migration to Python language justified by its applicability and portability in the artificial intelligence area, which enabled integration with prominent frameworks used in the current market for data processing, like Pandas, and data science, like Keras and Tensorflow. This new version of the hybrid system (ADEANN-Deep) using Keras/Tensorflow has expanded the possibility of the system to use various deep and recurrent Neural Network architectures.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Hybrid Approach for Energy Price Prediction in Brazilian Market

Campos¹,

Pereira²,

Duarte³

et al. 2020

Anais Do 14. Congresso Brasileiro De Inteligência Computacional

View full text Add to dashboard Cite

This paper proposes a hybrid approach for shortterm energy price prediction. This approach combines a genetic algorithm (GA) that evolves individuals represented by a set of production rules, these rules are extracted from chromosomes and generate the genotypes, which are mapped to phenotypes(Deep Neural Networks). The Artificial Neural Networks (ANNs) are then trained and then validated, and the prediction tests are carried out. The genotypes are classified by the performances of their ANNs in prediction and the GA selects the best individuals for mutation and crossover operations, which provide a new population. The previous steps are repeated through n generations. The result is an optimized neural network architecture for energy price prediction. The results show good ability to predict spikes and satisfactory accuracy according to error measures, delivering an accurate prediction. Finally, the results are compared with traditional techniques.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Hybrid Approach for Energy Price Prediction in Brazilian Market

Campos¹,

Pereira²,

Duarte³

et al. 2020

Anais Do 14. Congresso Brasileiro De Inteligência Computacional

View full text Add to dashboard Cite

show abstract

“…Com o uso cada vez mais disseminado do computador na educação, é cada vez maior a necessidade de estudá-lo como instrumento de mediação no processo de aprendizagem. (LEFFA, 2005, p. 29) Lima (2016)…”

unclassified

Propriedade Intelectual Para Criações De Inteligência Artificial

Souza¹,

Jacoski

2020

Os Impactos De Estudos Voltados Para as Ciências Exatas (Vol. 1)

View full text Add to dashboard Cite

“…Uma vez que a tarefa de sobrevivência se torna mais difícil e competitiva, exigindo comportamentos mais complexos, um processo evolutivo tende a criar seres cujas redes neurais são mais especializadas, que apresentem realimentações (redes recorrentes) apresentados, ampliando a complexidade e o repertório do comportamento. Com redes neurais de recorrentes, é possível prever uma nova classe de comportamentos De Campos et al, 2016],. que utiliza um conjunto de regras de produção para gerar arquiteturas de Redes Neurais Artificiais com N camadas.…”

unclassified