Access the full text.
Sign up today, get DeepDyve free for 14 days.
R Miikkulainen (2010)
Encyclopedia of Machine Learning, Chap. Neuroevolution
MM Cecchi, MR Zaglia (1993)
Computing the coefficients of a recurrence formula for numerical integration by moments and modified momentsJ. Comput. Appl. Math., 49
D Simon (2013)
Evolutionary Optimization Algorithms
PL Chebyshev (1858)
Sur les fractions continuesJ. Math. Pures Appl., 2
M Augasta, T Kathirvalavakumar (2013)
Pruning algorithms of neural networks - a comparative studyCent. Eur. J. Comput. Sci., 3
J Bergstra, Y Bengio (2012)
Random search for hyper-parameter optimizationJ. Mach. Learn. Res., 13
W Gautschi (2004)
Orthogonal Polynomials: Computation and Approximation. Numerical Mathematics and Scientific Computation
TJ Sullivan (2015)
Orthogonal Polynomials and Applications
S Samarasinghe (2017)
Neural Networks for Applied Sciences and Engineering: From Fundamentals to Complex Pattern Recognition
J Schmidhuber (2015)
Deep learning in neural networks: an overviewNeural Netw., 61
W Gautschi (1967)
Computational aspects of three-term recurrence relationsSIAM Rev., 9
X Yu, M Gen (2010)
Introduction to Evolutionary Algorithms
N Srivastava, G Hinton, A Krizhevsky, I Sutskever, R Salakhutdinov (2014)
Dropout: a simple way to prevent neural networks from overfittingJ. Mach. Learn. Res., 15
J Koza (1992)
Genetic programming: on the Programming of Computers by Means of Natural Selection
J Wang, H Wang, Y Chen, C Liu (2015)
A constructive algorithm for unsupervised learning with incremental neural networkJ. Appl. Res. Technol., 13
T Chihara (1978)
An Introduction to Orthogonal Polynomials
JC Principe, NR Euliano, WC Lefebvre (2000)
Neural and Adaptive Systems, Fundamentals Through Simulations
E Cheney (2000)
Introduction to Approximation Theory
J Couchet, D Manrique, J Porras (2007)
Grammar-guided neural architecture evolutionLect. Notes Comput. Sci, 4527
GH Golub, JH Welsch (1969)
Calculation of gauss quadrature rulesMath. Comp., 23
KO Stanley, R Miikkulainen (2004)
Competitive coevolution through evolutionary complexificationJ. Artif. Intell. Res., 21
P Bernardos, G Vosniakos (2007)
Optimizing feedforward artificial neural network architectureEng. Appl. Artif. Intel., 20
D Barrios Rolanía, G López Lagomasino, E Torrano (1995)
Location of zeros and asymptotics of polynomials satisfying three-terms recurrence relations with complex coefficientsRuss. Acad. Sci. Sb. Math., 80
J Font, D Manrique, P Ramos Criado, D del Río (2016)
Partition based real-valued encoding scheme for evolutionary algorithmsNat. Comput., 15
S Haykin (2010)
Neural Networks and Learning Machines
S Tapas, H Simanta, N Jana (2012)
Artificial neural network training using differential evolutionary algorithm for classificationAdv. Intel. Soft Comp., 132
L Pulina, A Tacchella (2011)
NeVer: a tool for artificial neural networks verificationAnn. Math. Artif. Intell., 62
K Jong (2006)
Evolutionary Computation: a Unified Approach
D Loiacono, L Cardamone, P Lanzi (2011)
Automatic track generation for high-end racing games using evolutionary computationIEEE Trans. Comput. Intell. AI Games, 3
L Kari, G Rozenberg (2008)
The many facets of natural computingCommun. ACM, 51
H Han, J Qiao (2013)
A structure optimisation algorithm for feedforward neural network constructionNeurocomputing, 99
G Huang, L Chen, C Siew (2006)
Universal approximation using incremental constructive feedforward networks with random hidden nodesIEEE Trans. Neural Netw., 17
R McKay, N Hoai, P Whigham, Y Shan, M O’Neill (1988)
Grammar-based genetic programming: a surveyGGenet. Program Evolvable Mach., 11
W Gautschi (2016)
Orthogonal Polynomials in Matlab. Exercises and Solutions. Software, Environments and Tools
K Hornik (1991)
Approximation capabilities of multilayer feedforward networksNeural Netw., 4
KO Stanley, R Miikkulainen (2002)
Evolving neural networks through augmenting topologiesEvol. Comput., 10
D Manrique, J Ríos, A Rodr(́i)guez-Patón (2006)
Artificial Neural Networks in Real Life Applications, Ch. Self-Adapting Neutral Intelligent Systems Using Evolutionary Techniques
This article presents an evolutionary algorithm to autonomously construct full-connected multilayered feedforward neural architectures. This algorithm employs grammar-guided genetic programming with a context-free grammar that has been specifically designed to satisfy three important restrictions. First, the sentences that belong to the language produced by the grammar only encode all valid neural architectures. Second, full-connected feedforward neural architectures of any size can be generated. Third, smaller-sized neural architectures are favored to avoid overfitting. The proposed evolutionary neural architectures construction system is applied to compute the terms of the two sequences that define the three-term recurrence relation associated with a sequence of orthogonal polynomials. This application imposes an important constraint: training datasets are always very small. Therefore, an adequate sized neural architecture has to be evolved to achieve satisfactory results, which are presented in terms of accuracy and size of the evolved neural architectures, and convergence speed of the evolutionary process.
Annals of Mathematics and Artificial Intelligence – Springer Journals
Published: Sep 18, 2018
Read and print from thousands of top scholarly journals.
Already have an account? Log in
Bookmark this article. You can see your Bookmarks on your DeepDyve Library.
To save an article, log in first, or sign up for a DeepDyve account if you don’t already have one.
Copy and paste the desired citation format or use the link below to download a file formatted for EndNote
Access the full text.
Sign up today, get DeepDyve free for 14 days.
All DeepDyve websites use cookies to improve your online experience. They were placed on your computer when you launched this website. You can change your cookie settings through your browser.