Designing Application-Specific Neural Networks Using the Genetic Algorithm

How researchers see this paper

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

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 [2, 9, 18, 26, 34, 43, 58, 64, 76, 77, 87, 92, 116, 124, 126].”
AI-GAs: AI-generating algorithms, an alternate paradigm for producing general artificial intelligence (2019, background): “However, there is also a long history in AI of creating algorithms to search for high-performing neural network architectures [90, 169, 55, 198, 59].”
Designing application-specific neural networks using the structured genetic algorithm (1992, methodology): “0 the overall designing of neural network architectures using genetic algorithms (Harp et al., 1989; Whitley et al., 1990; Harp et al., 1990; Miller et al., 1989; Maritit and Nikolov, 1990) that employ backpropagation(BP) learning algorithm for finding set of connection weights of the architecture”