Optimization schemes for neural network training

Chen, O.T.-C.; Sheu, B.J.

doi:10.1109/icnn.1994.374284

Cited by 7 publications

(1 citation statement)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The commonest and best-understood approach for off-line supervised learning is the gradient descent method: back-propagation [19]. Also, its computational cost is lower than the other methods (i.e., Newton, conjugate gradient) which leads to a faster convergence [20]. The weight correction, ) n ( w ji ∆ applied to the weights connecting neuron i to neuron j is defined by the delta rule:…”

Section: Supervised Learningmentioning

confidence: 99%

Intelligent Neurofuzzy Control of a Robotic Gripper

Domínguez-López

Damper

Crowder

et al. 2005

Innovations in Robot Mobility and Control

View full text Add to dashboard Cite

Section: Supervised Learningmentioning

confidence: 99%

Intelligent Neurofuzzy Control of a Robotic Gripper

Domínguez-López

Damper

Crowder

et al. 2005

Innovations in Robot Mobility and Control

View full text Add to dashboard Cite

Metaheuristic design of feedforward neural networks: A review of two decades of research

Ojha

Abraham

Snel

2017

Engineering Applications of Artificial Intelligence

442

154

View full text Add to dashboard Cite

Over the past two decades, the feedforward neural network (FNN) optimization has been a key interest among the researchers and practitioners of multiple disciplines. The FNN optimization is often viewed from the various perspectives: the optimization of weights, network architecture, activation nodes, learning parameters, learning environment, etc. Researchers adopted such different viewpoints mainly to improve the FNN's generalization ability. The gradient-descent algorithm such as backpropagation has been widely applied to optimize the FNNs. Its success is evident from the FNN's application to numerous real-world problems. However, due to the limitations of the gradient-based optimization methods, the metaheuristic algorithms including the evolutionary algorithms, swarm intelligence, etc., are still being widely explored by the researchers aiming to obtain generalized FNN for a given problem. This article attempts to summarize a broad spectrum of FNN optimization methodologies including conventional and metaheuristic approaches. This article also tries to connect various research directions emerged out of the FNN optimization practices, such as evolving neural network (NN), cooperative coevolution NN, complex-valued NN, deep learning, extreme learning machine, quantum NN, etc. Additionally, it provides interesting research challenges for future research to cope-up with the present information processing era.

show abstract