Deep Leaky Single-peaked Triangle Neural Networks

Shan, Chuanhui; Guo, Xirong; Ou, Jun

doi:10.1007/s12555-018-0796-0

Cited by 6 publications

(5 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deep learning algorithms have been developed to increase classification accuracy and stability (Shan et al, 2019 ; Park and Jung, 2020 ; Sung et al, 2020 ). RNNs have been developed to improve their performance likewise; memristor-based RNNs (Yang et al, 2021 ), chaotic delayed RNNs with unknown parameters and stochastic noise (Yan et al, 2019 ), reformed recurrent Hermite polynomial neural network (Lin and Ting, 2019 ).…”

Section: Discussionmentioning

confidence: 99%

Decoding Multiple Sound-Categories in the Auditory Cortex by Neural Networks: An fNIRS Study

Yoo

Santosa

Kim

2021

Front. Hum. Neurosci.

View full text Add to dashboard Cite

This study aims to decode the hemodynamic responses (HRs) evoked by multiple sound-categories using functional near-infrared spectroscopy (fNIRS). The six different sounds were given as stimuli (English, non-English, annoying, nature, music, and gunshot). The oxy-hemoglobin (HbO) concentration changes are measured in both hemispheres of the auditory cortex while 18 healthy subjects listen to 10-s blocks of six sound-categories. Long short-term memory (LSTM) networks were used as a classifier. The classification accuracy was 20.38 ± 4.63% with six class classification. Though LSTM networks’ performance was a little higher than chance levels, it is noteworthy that we could classify the data subject-wise without feature selections.

show abstract

Section: Discussionmentioning

confidence: 99%

Decoding Multiple Sound-Categories in the Auditory Cortex by Neural Networks: An fNIRS Study

Yoo

Santosa

Kim

2021

Front. Hum. Neurosci.

View full text Add to dashboard Cite

show abstract

“…represents the convolution process, Z(•) is the activation function. The rectifier linear unit (ReLU) [30] is used as the activation function, as shown in Equation ( 16):…”

Section: Convolution Layermentioning

confidence: 99%

A Detection Approach Using LSTM-CNN for Object Removal Caused by Exemplar-Based Image Inpainting

Niu

2020

Electronics

View full text Add to dashboard Cite

Exemplar-based image inpainting technology is a “double-edged sword”. It can not only restore the integrity of image by inpainting damaged or removed regions, but can also tamper with the image by using the pixels around the object region to fill in the gaps left by object removal. Through the research and analysis, it is found that the existing exemplar-based image inpainting forensics methods generally have the following disadvantages: the abnormal similar patches are time-consuming and inaccurate to search, have a high false alarm rate and a lack of robustness to multiple post-processing combined operations. In view of the above shortcomings, a detection method based on long short-term memory (LSTM)-convolutional neural network (CNN) for image object removal is proposed. In this method, CNN is used to search for abnormal similar patches. Because of CNN’s strong learning ability, it improves the speed and accuracy of the search. The LSTM network is used to eliminate the influence of false alarm patches on detection results and reduce the false alarm rate. A filtering module is designed to eliminate the attack of post-processing operation. Experimental results show that the method has a high accuracy, and can resist the attack of post-processing combination operations. It can achieve a better performance than the state-of-the-art approaches.

show abstract

“…An AF similar to vReLU, AbsLU, and tent activation named leaky single-peaked triangle linear unit (LSPTLU) was proposed in [271]. It is defined as…”

Section: Absolute Linear Unit (Abslu)mentioning

confidence: 99%

“…where a is a fixed parameter [271]. An identical AF was proposed under the name leaky rectified triangle linear unit (LRTLU) in [272].…”

Section: Absolute Linear Unit (Abslu)mentioning

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

Deep Leaky Single-peaked Triangle Neural Networks

Cited by 6 publications

References 8 publications

Decoding Multiple Sound-Categories in the Auditory Cortex by Neural Networks: An fNIRS Study

Decoding Multiple Sound-Categories in the Auditory Cortex by Neural Networks: An fNIRS Study

A Detection Approach Using LSTM-CNN for Object Removal Caused by Exemplar-Based Image Inpainting

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

Contact Info

Product

Resources

About