Designing application-specific neural networks using the structured genetic algorithm

By Dipankar Dasgupta, Douglas R. McGregor. 1992

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].”
Evolutionary Computation for Reinforcement Learning (2012, background): “Perhaps the earliest and simplest TWEANN is the structured genetic algorithm (sGA) (Dasgupta and McGregor, 1992), which uses a two-part representation to describe each network.”
Efficient Reinforcement Learning Through Evolving Neural Network Topologies (2002, methodology): “For example, the NEAT method may be applied to the evolution of hardware (Miller et al. 200a,b), cellular automata ( Mitchell et al. 1996 ), or genetic programs (Koza 1992).”
Real-time neuroevolution in the NERO video game (2005, background): “While some evolve only the connection weight values of fixed-topology networks [37], [47]–[49], others evolve both weights and network topology simultaneously [38], [50]–[62].”
Evolving Neural Networks through Augmenting Topologies (2002, methodology): “The average solution had 2.35 hidden nodes with a standard deviation of 1.11 nodes. ficult in this domain because the methodologies vary widely across experiments (Dasgupta and McGregor, 1992; Pujol and Poli, 1998; Yao and Shi, 1995; Zhang and M ¨ uhlenbein, 1993).”
Metaheuristic design of feedforward neural networks: A review of two decades of research (2017, methodology): “A structured genetic algorithm was proposed in [263], which simultaneously optimized both architectures and weights.”
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].”