Training Feedforward Neural Networks Using Genetic Algorithms

By D. Montana, L. Davis. 1989

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

Evolving Deep Neural Networks (2017, methodology): “Neuroevolution techniques have been applied successfully to sequential decision tasks for three decades [11, 31, 36, 50].”
Training feedforward neural networks using hybrid particle swarm optimization and gravitational search algorithm (2012, methodology): “Various heuristic optimization methods have been used to train FNNs, such as Simulated Annealing (SA) [12,13], Genetic Algorithms (GAs) [14], Particle Swarm Optimization (PSO) algorithms [15–19], Magnetic Optimization Algorithm (MOA) [20], and Differential Evolution (DE) [21].”
Evolving artificial neural networks (1999, background): “Montana and Davis [27] deﬁned a large number of tailored genetic operators which incorporated many heuristics about training ANN’s.”
Evolving Neural Networks through Augmenting Topologies (2002, background): “Past studies have shown NE to be faster and more efficient than reinforcement learning methods such as Adaptive Heuristic Critic and Q-Learning on single pole balancing and robot arm control (Moriarty and Miikkulainen, 1996; Moriarty, 1997).”
Evolutionary Algorithms for Neural Network Design and Training (1995, background): “Montana and Davis [52] did not (cid:12)nd signi(cid:12)cant di(cid:11)erences between an operator that always transferred all incoming weights of a node to the o(cid:11)spring and one that worked on single weight values.”
Evolving Artiicial Neural Networks (2007, background): “Montana and Davis [27] de ned a large numberof tailored genetic operators which incorporated many heuristics about training ANNs.”
Efficient Reinforcement Learning Through Evolving Neural Network Topologies (2002, background): “The historical markings give NEAT a powerful new capability , effectively avoiding the problem of competing conventions (Montana and Davis 1989; Radcliffe 1993; Schaffer et al. 1992).”
Neuroevolution: from architectures to learning (2008, background): “In a classic study, Montana and Davis [ 51 ] compared the performance of synaptic weight evolution with a discrete direct representation with that of the back-propagation”
Simultaneous optimization of artificial neural networks for financial forecasting (2012, background): “Finally, GA tends to converge on an optimal or near-optimal solution through these operators [32].”
A comprehensive survey on machine learning for networking: evolution, applications and research opportunities (2018, methodology): “Bioinspired optimization algorithms, such as Genetic Algorithms (GA) and Particle Swarm Optimization (PSO), received increasing attention and were used to train NNs for improved performance over the traditional BP-based learning [234, 319].”
G-Prop-III: Global Optimization of Multilayer Perceptrons using an Evolutionary Algorithm (1999, methodology): “This operator is used to train the individual-net for a certain number of generations, using the QP algorithm, as suggested in [29] and [19].”
Metaheuristic design of feedforward neural networks: A review of two decades of research (2017, background): “, were defined, for operating on the real-valued chromosome [147].”
Deep Code Search (2018, background): “…have no strict order in the source code, they are simply embedded via a multilayer perceptron (MLP), i.e., the conventional fully connected layer [52]: where τ i ∈ R d represents the embedded representation of the to-ken τ i , W Γ is the matrix of trainable parameters in the MLP, h i , i = 1 ,…”