Optimization for problem classes-neural networks that learn to learn

33 citations recorded by the source corpus.

How researchers see this paper

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

Population Based Training of Neural Networks (2017, background): “…2006) or where the hyperparameters, initial weights, and architecture of networks are evolved, but the parameters are learned (Castillo et al., 1999; Husken et al., 2000), or where evolution and learning are both applied to the parameters (Ku & Mak, 1997; Houck et al., 1997; Igel et al., 2005).”
The Influence of Learning on Evolution: A Mathematical Framework (2009, background): “, [7, 15, 19]), while at the same time it has been demonstrated that this so-called Lamarckian inheritance has an adaptive disadvantage in quickly changing environments [30, 33].”