A review of evolutionary artificial neural networks

By Xin Yao. 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

Deep learning in neural networks: An overview (2014, background): “…proposed (e.g., Cliff, Husbands, & Harvey, 1993; Juang, 2004; Miglino, Lund, & Nolfi, 1995; Miller, Todd, & Hedge, 1989; Moriarty, 1997; Nolfi, Floreano, Miglino, & Mondada, 1994; Pasemann, Steinmetz, & Dieckman, 1999; Sims, 1994; Whiteson, 2012; Wieland, 1991; Yamauchi & Beer, 1994; Yao, 1993).”
On Learning to Think: Algorithmic Information Theory for Novel Combinations of Reinforcement Learning Controllers and Recurrent Neural World Models (2015, methodology): “1, except that C is now an FNN or RNN trained by evolutionary algorithms [200, 255, 105, 56, 68] applied to NNs [165, 321, 180, 259, 72, 90, 89, 110, 94], or by policy gradient methods [314, 315, 316, 274, 18, 1, 63, 128, 313, 210, 192, 191, 256, 85, 312, 190, 82, 93][245, Sec.”
One Big Net For Everything (2018, neutral): “, through artificial evolution [39, 107, 83, 40, 16, 18, 103, 14, 89, 88] [76, Sec.”
Self-Delimiting Neural Networks (2012, methodology): “A more general approach for partially observable environmen ts directly evolves programs for RNNs with internal states (no need for the Markovian assumption), by a pplying evolutionary algorithms [45, 68, 28] to RNN weight matrices [82, 70, 72, 25].”
Evolino for recurrent support vector machines (2005, unknown): “This idea of evolving neural networks using artificial evolution or neuroevolution [25] is normally”
Evolutionary artificial neural networks: a review (2011, methodology): “This is mainly manifested in using EAs to optimize the network design, pre-process the network input data, the assemble of ANNs (Yao 1993), etc.”
Robust non-linear control through neuroevolution (2003, background): “Recently, significant progress has been made in solving continuous, non-Markov reinforcement learning problems using methods that evolve neural networks or neuroevolution (NE; Yamauchi and Beer 1994; Nolfi and Parisi 1995; Yao 1993; Moriarty 1997).”
Hardware spiking neural network with run-time reconfigurable connectivity in an autonomous robot (2003, background): “Direct codings [33] are not very flexible in cases where new cells are added to the system (no bits are available to give a function to that cell), or when the system reorganizes, because the number of elements in the system must be known in advance and cannot change throughout the life of the syste”
Evolutionary robotics: coping with environmental change (2000, background): “Synapse Encoding: also known as direct encoding (Yao, 1993), every synapse is individually coded on 5 bits, the first bit representing its sign and the remaining four bits its properties (either the weight strength or its adaptive rule).”
Gradient boosting machines, a tutorial (2013, methodology): “If we consider connections to earlier developments, it will turn out that the well known cascade correlation neural networks (Fahlman and Lebiere, 1989; Yao, 1993) can be considered a special type of a gradient boosted model, as defined in Algorithm 1.”
Driven by Compression Progress: A Simple Principle Explains Essential Aspects of Subjective Beauty, Novelty, Surprise, Interestingness, Attention, Curiosity, Creativity, Art, Science, Music, Jokes (2008, unknown): “Many approaches to evolving RNNs have been proposed [34, 111 , 110, 37, 33, 93, 35, 15].”
Training Recurrent Networks by Evolino (2007, methodology): “more efficient and principled way is to search the space of RNN weight matrices [20,21,26,45,53,54] using evolutionary algorithms [1 3,31,41].”
Meta-learning for evolutionary parameter optimization of classifiers (2012, methodology): “For instance, architecture, weights, and learning parameters of artificial neural networks were optimized using such evolutionary approaches by Yao (1993).”