A new evolutionary system for evolving artificial neural networks

By Xin Yao, Yong Liu. 1997

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

Born to Learn: the Inspiration, Progress, and Future of Evolved Plastic Artificial Neural Networks (2017, methodology): “Popular algorithms include early work of Angeline et al. (1994) and Yao and Liu (1997) to evolve neural networks, Neuroevolution of Augmenting Topologies (NEAT) (Stanley and Miikkulainen, 2002), Analog Genetic Encoding (AGE) (Mattiussi and Flo-reano, 2007), and HyperNEAT (Stanley et al., 2009).”
Evolutionary ensembles with negative correlation learning (2000, background): “This paper presents evolutionary ensembles with negative correlation learning (EENCL) for designing NN ensembles automatically based on negative correlation learning [13, 14, 15] and evolutionary learning [16, 1, 17].”
A survey of neural network techniques in market trend analysis (2017, methodology): “Using an iterative approach for refinement that uses probabilistic incremental program evolution algorithm (PIPE) for the structure and simulated annealing for parameter tuning, the optimal neural tree is constructed for a market[8], [9].”
Tuning the structure and parameters of a neural network by using hybrid Taguchi-genetic algorithm (2006, background): “Therefore, recently, some researchers (for example, see [3], [10], [17]–[27], and references therein) have proposed various methods to solve the problem of learning the network structure and the connecting weights, where, in general, the network structure is considered to be a fully connected networ”
Artificial Bee Colony (ABC) Optimization Algorithm for Training Feed-Forward Neural Networks (2007, unknown): “Evolutionary Programming algorithms [30,31,32].”
Spectrum-Diverse Neuroevolution With Unified Neural Models (2017, unknown): “Acquisition of Recurrent Links [14], NEAT [15], Evolutionary Acquisition of Neural Topologies [16], and EPNet [17].”
Metaheuristic design of feedforward neural networks: A review of two decades of research (2017, background): “problem in a GA, EP-based mutation mechanism for evolving FNN architecture was proposed in [258] is known as EPNet.”
RENAS: Reinforced Evolutionary Neural Architecture Search (2019, methodology): “Thus, many early automatic architecture search methods [26, 37, 32, 29, 25, 36] adopt EA to evolve a population of models.”
Neural networks for the prediction and forecasting of water resource variables: a review of modelling issues and applications (2000, methodology): “A number of algorithms based on Fogel’s evolutionary programming (Fogel et al., 1966) have been proposed to overcome these problems (e.g. Angeline et al., 1994; Yao and Liu, 1997).”
Applying LSTM to Time Series Predictable through Time-Window Approaches (2000, background): “EPNet [15]: Evolved neural nets (Evolvable Programming Net).”
A New Adaptive Merging and Growing Algorithm for Designing Artificial Neural Networks (2009, methodology): “For example, EPNet required on average of 109 000 epochs for a single run [61], while AMGA required less than 1000 epochs (Table II).”