Combinations of genetic algorithms and neural networks: a survey of the state of the art

By J. Schaffer, L. D. Whitley, L. Eshelman. 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

A genetic programming approach to designing convolutional neural network architectures (2017, methodology): “Evolutionary algorithms have been used to optimize neural network architectures so far [26, 32].”
Designing Neural Network Architectures using Reinforcement Learning (2016, background): “Designing neural network architectures: Research on automating neural network design goes back to the 1980s when genetic algorithm-based approaches were proposed to ﬁnd both architectures and weights (Schaffer et al., 1992).”
Adding Learning to the Cellular Development of Neural Networks: Evolution and the Baldwin Effect (1993, methodology): “A survey of this work is given by Schaffer, Whitley, and Eshelman (1992) in an introduction to the proceedings of a workshop, Combinations of Genetic Algorithms and Neural Networks.”
A new evolutionary system for evolving artificial neural networks (1997, background): “The evolution of ANN architectures in general suffers from the permutation problem [27], [28] or called competing conventions problem [17].”
Hardware/Software Co-Exploration of Neural Architectures (2019, unknown): “Although the research on the automatic prediction of neural network architectures can trace back to the 1980s [25], after DNNs have achieved great success in AI domains, there have been growing interests in generating good neural architectures for the interested dataset recently.”
Practical Block-Wise Neural Network Architecture Generation (2017, background): “Early works, from 1980s, have made efforts on automating neural network design which often searched good architecture by the genetic algorithm or other evolutionary algorithms [24, 27, 26, 28, 23, 7, 34].”
Evolving structure and function of neurocontrollers (1999, methodology): “In contrast to genetic algorithms, which are often only used for optimizing a specific feedforward architecture [ 8 ], [11], it does not quantize the network parameters like weights and bias terms.”
A New Adaptive Merging and Growing Algorithm for Designing Artificial Neural Networks (2009, background): “A large number of ANN design algorithms have been proposed based on evolutionary approaches (see the review papers [ 38 ]–[40]).”
Accuracy vs. Efficiency: Achieving Both through FPGA-Implementation Aware Neural Architecture Search (2019, background): “MNIST 60,000 10,000 25 4 [5,7,14] [9,18,36] 60 TS-High TS-Low”
BlockQNN: Efficient Block-Wise Neural Network Architecture Generation (2018, methodology): “Early methods [30], [31], [32] simultaneously evolve the topology of neural networks along with the weights and hyperparameters.”
Incremental Learning in Biological and Machine Learning Systems (2002, background): “Several reviews show that evolutionary artificial neural networks have been investigated and applied successfully in recent years.(104,125,142,146) According to Yao(146) evolution in artificial neural networks can include adaption of connection weights (an alternative to standard network training, s”