Wind speed forecasting using genetic programming

Graff, Mario; Capilla, Rafael Peña; Medína, A.

doi:10.1109/cec.2013.6557598

Cited by 20 publications

(9 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [40], gradient descent is used and tested on classification problems, while [13] uses Resilient Backpropagation (RPROP) and evaluates the proposal on a real-world problem. In [40], the authors apply gradient descent on every individual of the evolving population, an obvious computational bottleneck, while [13] only applies RPROP on the best individual from each generation. However, it is not evident which strategy can offer the best results in new scenarios, particularly since both [40,13] evaluate their approaches on specific problem instances.…”

Section: Previous Workmentioning

confidence: 99%

“…Additionally, that work only considers training fitness, a highly deceptive measure of learning. Similarly, in [40] and [13] a LS algorithm is used to optimize the value of constant terminal elements. In [40], gradient descent is used and tested on classification problems, while [13] uses Resilient Backpropagation (RPROP) and evaluates the proposal on a real-world problem.…”

Section: Previous Workmentioning

confidence: 99%

“…Similarly, in [40] and [13] a LS algorithm is used to optimize the value of constant terminal elements. In [40], gradient descent is used and tested on classification problems, while [13] uses Resilient Backpropagation (RPROP) and evaluates the proposal on a real-world problem. In [40], the authors apply gradient descent on every individual of the evolving population, an obvious computational bottleneck, while [13] only applies RPROP on the best individual from each generation.…”

Section: Previous Workmentioning

confidence: 99%

“…For instance, some researchers apply the LS to the best solution in the population, but [32] [3] 178 13 Chemical analysis of wines Sonar [3] 208 60 Sonar signals off metal cylinder at various angles and conditions Wholesale [3] 440 8 Clients information of wholesale distributor Banknote [3] 1372 5 Image information from genuine & forged banknote-like specimens LSVT [34] 126 309 Signal data from speech rehabilitation treatment on Parkinson patients showed that better results are obtained when it is applied to all the population or a subset of the best solutions in each generation. However, in our case, the number of parameters grows proportionally with the size of the trees, providing incentive to limit the amount of times the LS is applied, especially for larger trees.…”

Section: Integrating Ls Into Gpmentioning

confidence: 99%

See 3 more Smart Citations

A Local Search Approach to Genetic Programming for Binary Classification

Z-Flores

Trujillo

Schütze

et al. 2015

Proceedings of the 2015 Annual Conference on Genetic and Evolutionary Computation

View full text Add to dashboard Cite

In standard genetic programming (GP), a search is performed over a syntax space defined by the set of primitives, looking for the best expressions that minimize a cost function based on a training set. However, most GP systems lack a numerical optimization method to fine tune the implicit parameters of each candidate solution. Instead, GP relies on more exploratory search operators at the syntax level. This work proposes a memetic GP, tailored for binary classification problems. In the proposed method, each node in a GP tree is weighted by a real-valued parameter, which is then numerically optimized using a continuous transfer function and the Trust Region algorithm is used as a local search method. Experimental results show that potential classifiers produced by GP are improved by the local searcher, and hence the overall search is improved achieving significant performance gains, that are competitive with state-of-the-art methods on well-known benchmarks.

show abstract

Section: Previous Workmentioning

confidence: 99%

Section: Previous Workmentioning

confidence: 99%

Section: Previous Workmentioning

confidence: 99%

Section: Integrating Ls Into Gpmentioning

confidence: 99%

See 2 more Smart Citations

A Local Search Approach to Genetic Programming for Binary Classification

Z-Flores

Trujillo

Schütze

et al. 2015

Proceedings of the 2015 Annual Conference on Genetic and Evolutionary Computation

View full text Add to dashboard Cite

show abstract

“…Similarly, in [26] and [7] a LS algorithm is used to optimize the value of constant terminal elements. In [26] gradient descent is used and tested on classification problems, while [7] uses resilient backpropagation and evaluates the proposal on a real-world problem, in both cases leading towards improved results. In [17], the authors include weight parameters for each function node, what the authors call inclusion factors; these weights modulate the importance that each node has within the tree.…”

Section: Local Search In Standard Genetic Programmingmentioning

confidence: 99%

Geometric Semantic Genetic Programming with Local Search

Castelli

Trujillo

Vanneschi

et al. 2015

Proceedings of the 2015 Annual Conference on Genetic and Evolutionary Computation

View full text Add to dashboard Cite

Since its introduction, Geometric Semantic Genetic Programming (GSGP) has aroused the interest of numerous researchers and several studies have demonstrated that GSGP is able to effectively optimize training data by means of small variation steps, that also have the effect of limiting overfitting. In order to speed up the search process, in this paper we propose a system that integrates a local search strategy into GSGP (called GSGP-LS). Furthermore, we present a hybrid approach, that combines GSGP and GSGP-LS, aimed at exploiting both the optimization speed of GSGP-LS and the ability to limit overfitting of GSGP. The experimental results we present, performed on a set of complex real-life applications, show that GSGP-LS achieves the best training fitness while converging very quickly, but severely overfits. On the other hand, GSGP converges slowly relative to the other methods, but is basically not affected by overfitting. The best overall results were achieved with the hybrid approach, allowing the search to converge quickly, while also exhibiting a noteworthy ability to limit overfitting. These results are encouraging, and suggest that future GSGP algorithms should focus on finding the correct balance between the greedy optimization of a local search strategy and the more robust geometric semantic operators.

show abstract

Combining Geometric Semantic GP with Gradient-Descent Optimization

Pietropolli

Manzoni

Paoletti

et al. 2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Geometric semantic genetic programming (GSGP) is a wellknown variant of genetic programming (GP) where recombination and mutation operators have a clear semantic effect. Both kind of operators have randomly selected parameters that are not optimized by the search process. In this paper we combine GSGP with a well-known gradientbased optimizer, Adam, in order to leverage the ability of GP to operate structural changes of the individuals with the ability of gradient-based methods to optimize the parameters of a given structure. Two methods, named HYB-GSGP and HeH-GSGP, are defined and compared with GSGP on a large set of regression problems, showing that the use of Adam can improve the performance on the test set. The idea of merging evolutionary computation and gradient-based optimization is a promising way of combining two methods with very different -and complementary -strengths.

show abstract

Wind speed forecasting using genetic programming

Cited by 20 publications

References 47 publications

A Local Search Approach to Genetic Programming for Binary Classification

A Local Search Approach to Genetic Programming for Binary Classification

Geometric Semantic Genetic Programming with Local Search

Combining Geometric Semantic GP with Gradient-Descent Optimization

Contact Info

Product

Resources

About