Evolving Optimal Neural Networks Using Genetic Algorithms with Occam's Razor

By Byoung-Tak Zhang, Heinz Mühlenbein. 1993

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

Tuning the structure and parameters of a neural network by using hybrid Taguchi-genetic algorithm (2006, background): “In addition, among these researchers of studying the mentioned-above problem, Leung et al. [10], [19], Yao [18] Koza and Rice [20], Maniezzo [21], Zhang and Muhlenbein [ 22 ], Richards et al. [25], and Curran and O’Riordan [27] studied the problem of simultaneously tuning both network structure and ”
Evolutionary design of neural network tree-integration of decision tree, neural network and GA (2001, methodology): “3. Design a tree structured NN using genetic programming (GP) [7]-[ 8 ].”
Using ant colony optimization to optimize long short-term memory recurrent neural networks (2018, methodology): “In traditional neuroevolution [28], an evolutionary algorithm is used to train a neural networks’ connection weights with a fixed structure, but significant benefit has been demonstrated in using these techniques to both optimize and evolve connections and topologies [9, 12, 26], as weights are not…”
Real-time neuroevolution in the NERO video game (2005, background): “Other systems that evolve network topologies and weights begin evolution with a population of random topologies [38], [46], [54], [58].”
Compositional pattern producing networks: A novel abstraction of development (2007, methodology): “methods already exist for evolving ANN topology and weights [5, 32, 58, 61, 73, 83, 84 ].”
Evolving Neural Networks through Augmenting Topologies (2002, background): “Some have argued that network complexity can affect the speed and accuracy of learning (Zhang and M ¨ uhlenbein, 1993).”
Evolutionary Computation for Reinforcement Learning (2012, background): “It is possible to explicitly reward smaller solutions by adding size penalties in the fitness function (Zhang and Muhlenbein, 1993).”
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].”
Autonomous Evolution of Topographic Regularities in Artificial Neural Networks (2010, methodology): “…Pollack, 2000; Montana & Davis, 1989; Moriarty & Miikkulainen, 1996; Opitz & Shavlik, 1997; Pujol & Poli, 1998; Sims, 1994; Srinivas & Paranaik, 1991; Stanley & Miikkulainen, 2002b; Yao, 1999; Zhang & Muhlenbein, 1993), the neurons within a HyperNEAT substrate are situated at geometric coordinates.”
Compositional Pattern Producing Networks : A Novel Abstraction of Development (2007, background): “It is fortuitous that CPPNs and ANNs are virtually the same from a structural perspective because many methods already exist for evolving ANN topology and weights [5, 32, 58, 61, 73, 83, 84].”