Predictions of bridge scour: Application of a feed-forward neural network with an adaptive activation function

Ismail, Anis; Jeng, Dong‐Sheng; Zhang, L. L.; Zhang, J. S.

doi:10.1016/j.engappai.2012.12.011

Cited by 35 publications

(14 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A different approach represents the network in network (NIN) [34] which uses a micro neural network as an adaptive activation function. Another approach employs a gated linear combination of activation functions for each neuron which allows each neuron to choose which activation function (from an existing pool) it may use for minimizing the error [16]; a similar method uses just binary indicators instead of the gates [35]. The adaptive activation function might also be trained in a semi-supervised manner [36]- [38].…”

Section: Adaptive Activation Functionsmentioning

confidence: 99%

On Transformative Adaptive Activation Functions in Neural Networks for Gene Expression Inference

Kunc

Kléma²

2019

Preprint

View full text Add to dashboard Cite

Motivation: Gene expression profiling was made cheaper by the NIH LINCS program that profiles only ∼1, 000 selected landmark genes and uses them to reconstruct the whole profile. The D-GEX method employs neural networks to infer the whole profile. However, the original D-GEX can be further significantly improved. Results: We have analyzed the D-GEX method and determined that the inference can be improved using a logistic sigmoid activation function instead of the hyperbolic tangent. Moreover, we propose a novel transformative adaptive activation function that improves the gene expression inference even further and which generalizes several existing adaptive activation functions. Our improved neural network achieves average mean absolute error of 0.1340 which is a significant improvement over our reimplementation of the original D-GEX which achieves average mean absolute error 0.1637

show abstract

Section: Adaptive Activation Functionsmentioning

confidence: 99%

On Transformative Adaptive Activation Functions in Neural Networks for Gene Expression Inference

Kunc

Kléma²

2019

Preprint

View full text Add to dashboard Cite

show abstract

“…The extreme version of this approach consists in having an activation function that is modified during the training procedure, creating in fact an ad hoc transfer function for neurons. Variations of this approach can be found for problems of biomedical signal processing [34], structural analysis [35], and data mining procedures [36]. The training algorithm for such networks requires taking into consideration the activation function adaptation, as well as the weights tuning.…”

Section: Activation Functions For Easy Trainingmentioning

confidence: 99%

On Training Efficiency and Computational Costs of a Feed Forward Neural Network: A Review

Laudani

Lozito

Fulginei

et al. 2015

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

A comprehensive review on the problem of choosing a suitable activation function for the hidden layer of a feed forward neural network has been widely investigated. Since the nonlinear component of a neural network is the main contributor to the network mapping capabilities, the different choices that may lead to enhanced performances, in terms of training, generalization, or computational costs, are analyzed, both in general-purpose and in embedded computing environments. Finally, a strategy to convert a network configuration between different activation functions without altering the network mapping capabilities will be presented.

show abstract

“…Reviewing the literature surveys shows that other soft computing methods, e.g., artificial neural networks have been used to predict scouring depth [17][18][19][20]. These studies' explorations showed that using the neural network approach may result in better outcomes than empirical relations [21].…”

Section: Introductionmentioning

confidence: 96%

Hybrid ANFIS–PSO approach for predicting optimum parameters of a protective spur dike

Basser

Karami

Shamshirband

et al. 2015

Applied Soft Computing

View full text Add to dashboard Cite

Predictions of bridge scour: Application of a feed-forward neural network with an adaptive activation function

Cited by 35 publications

References 18 publications

On Transformative Adaptive Activation Functions in Neural Networks for Gene Expression Inference

On Transformative Adaptive Activation Functions in Neural Networks for Gene Expression Inference

On Training Efficiency and Computational Costs of a Feed Forward Neural Network: A Review

Hybrid ANFIS–PSO approach for predicting optimum parameters of a protective spur dike

Contact Info

Product

Resources

About