Genetic evolution of the topology and weight distribution of neural networks

By V. Maniezzo. 1994

How researchers see this paper

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

Citations in the corpus

Weight Agnostic Neural Networks (2019, background): “Our work has connections to existing work not only in deep learning, but also to various other ﬁelds: Architecture Search Search algorithms for neural network topologies originated from the ﬁeld of evolutionary computing in the 1990s [1, 8, 17, 25, 33, 40, 53, 59, 70, 71, 81, 86, 116, 117].”
Deep learning in neural networks: An overview (2014, background): “Here several policies are represented by a population of NNs improved through mutatio ns and/or repeated recombinations of the population’s fittest individuals (e.g., Montana and Davis, 1989; Fogel et al., 1990; Maniezzo, 1994; Happel and Murre, 1994; Nolfi et al., 1994b).”
An evolutionary artificial neural networks approach for breast cancer diagnosis (2002, background): “This problem has been tackled by the evolutionary approach in many studies [4, 14, 17, 21, 24, 39, 40, 41].”
Metaheuristic design of feedforward neural networks: A review of two decades of research (2017, methodology): “It was found that the simultaneous optimization of both weight and architecture lead to a better generalization [56, 197, 264, 265].”
Tuning of the structure and parameters of neural network using an improved genetic algorithm (2001, unknown): “An ANNA ELEONORA algorithm was proposed [36].”
Real-time neuroevolution in the NERO video game (2005, background): “While so me evolve only the connection weight values of fixed-topology networks (Gomez and Miikkulainen 1 999; Moriarty and Miikkulainen 1996a; Saravanan and Fogel 1995; Wieland 1991), others evolve both wei ghts and network topology simultaneously (Angeline et al. 1993; Bongard and Pfeifer 2001; Br”
Evolving artificial neural networks (1999, background): “One way to alleviate this problem is to evolve ANN architectures and connection weights simultaneously [37], [42], [45], [149], [165], [166], [169]–[172], [179], [180], [182], [185]–[200], [230], [232].”
Evolution of an artificial neural network based autonomous land vehicle controller (1996, methodology): “This network is used as the basis of the solution encodings for PBIL; a similar scheme has been used in [ 22 ].”
Evolving Artiicial Neural Networks (2007, background): “One way to alleviate this problem is to evolve ANN architectures and connection weights simultaneously [230, 165, 171, 169, 170, 166, 42, 45, 37, 172, 232, 179, 180, 182, 185, 186, 187, 188, 189, 190, 191, 192, 193, 194, 195, 196, 197, 149, 198, 199, 200].”
Evolution of neural networks using Cartesian Genetic Programming (2010, background): “Direct encoding are generally thought of as better at fine tuning and generating compact architecture [1], [12], [25], [3], [19], [26], [14].”
Evolution of homing navigation in a real mobile robot (1996, methodology): “Several methods [40], [41], [42], [43], [44], [45] have been proposed and shown to yield better and faster solutions than traditional encoding methods on simple tasks, but only a few [46], [36] have been applied to autonomous agents.”
Analog Genetic Encoding for the Evolution of Circuits and Networks (2007, methodology): “The direct encoding has been applied to the synthesis of electronic circuits [4]–[6] and neural networks [7]–[11].”
Evolutionary Algorithms for Neural Network Design and Training (1995, methodology): “Maniezzo [45, 46] (optimizing weights and structure at the same time) used binary encoding, but additionally included a granularity parameter in the genotype to simultaneously optimize how many bits should be used to encode one weight value.”
Simultaneous optimization of artificial neural networks for financial forecasting (2012, methodology): “Maniezzo [28], Williamson [57], and other recent research [19, 25] have used GA as the method to determine the optimal topology of ANN.”
An integrated growing-pruning method for feedforward network training (2008, methodology): “Example training algorithms are backpropagation [26,19], Levenberg Marquardt [13], Genetic Algorithms [2,8,22], cascade correlation (CC) [12] and OWO-HWO [5] which is described in the next subsection.”
A new evolutionary system for evolving artificial neural networks (1997, background): “Although the idea of evolving both architectures and weights is not new [3], [10], [13], [26], few have explained why it is important in terms of accurate fitness evaluation.”
Artificial immune systems as a novel soft computing paradigm (2003, background): “For example, they can be used to evolve artificial neural network architectures (Harrald and Kamstra, 1997; Maniezzo, 1994; Friedrich and Moraga, 1996; Opitz and Shavlik, 1997) or to design fuzzy systems (Chan et al., 1997; Shi et al., 1999; Belarbi and Titel, 2000).”