A Comparison of Regularization Techniques in Deep Neural Networks

Nusrat, Ismoilov; Jang, Sung-Bong

doi:10.3390/sym10110648

Cited by 92 publications

(55 citation statements)

References 42 publications

(34 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…If the data contain highly correlated features, then the machine learning algorithms, in general, perform poorly. Regularization techniques are used to overcome the issues of overfitting whereas underfitting would require the acquisition of more data and that is not an issue in the case of big data [32].…”

Section: A Data Acquisitionmentioning

confidence: 99%

Smart Grid Big Data Analytics: Survey of Technologies, Techniques, and Applications

et al. 2021

View full text Add to dashboard Cite

Smart grids have been gradually replacing the traditional power grids since the last decade. Such transformation is linked to adding a large number of smart meters and other sources of information extraction units. This provides various opportunities associated with the collected big data. Hence, the triumph of the smart grid energy paradigm depends on the factor of big data analytics. This includes the effective acquisition, transmission, processing, visualization, interpretation, and utilization of big data. The paper provides deep insights into various big data technologies and discusses big data analytics in the context of the smart grid. The paper also presents the challenges and opportunities brought by the advent of machine learning and big data from smart grids. INDEX TERMS Big data, data analytics, smart grid, big data management, machine learning.

show abstract

Section: A Data Acquisitionmentioning

confidence: 99%

Smart Grid Big Data Analytics: Survey of Technologies, Techniques, and Applications

et al. 2021

View full text Add to dashboard Cite

show abstract

“…The technical reasons for SCL picking both CNN and LSTM to defend against LFA in IoT networks are twofold. First, the conventional deep learning approaches, which apply a single constituent learning algorithm, often encounter overfitting problems [ 31 , 32 , 33 ]. Overfitting is when the model is trained exactly to a particular set of data and unwittingly extracts variation (i.e., the noise), as if that variation represents underlying population structure; in such cases, the model may therefore fail to fit additional data or predict future observations.…”

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A Spatiotemporal-Oriented Deep Ensemble Learning Model to Defend Link Flooding Attacks in IoT Network

Chen

Lai

Jan

et al. 2021

Sensors

View full text Add to dashboard Cite

(1) Background: Link flooding attacks (LFA) are a spatiotemporal attack pattern of distributed denial-of-service (DDoS) that arranges bots to send low-speed traffic to backbone links and paralyze servers in the target area. (2) Problem: The traditional methods to defend against LFA are heuristic and cannot reflect the changing characteristics of LFA over time; the AI-based methods only detect the presence of LFA without considering the spatiotemporal series attack pattern and defense suggestion. (3) Methods: This study designs a deep ensemble learning model (Stacking-based integrated Convolutional neural network–Long short term memory model, SCL) to defend against LFA: (a) combining continuous network status as an input to represent “continuous/combination attacking action” and to help CNN operation to extract features of spatiotemporal attack pattern; (b) applying LSTM to periodically review the current evolved LFA patterns and drop the obsolete ones to ensure decision accuracy and confidence; (c) stacking System Detector and LFA Mitigator module instead of only one module to couple with LFA detection and mediation at the same time. (4) Results: The simulation results show that the accuracy rate of SCL successfully blocking LFA is 92.95%, which is 60.81% higher than the traditional method. (5) Outcomes: This study demonstrates the potential and suggested development trait of deep ensemble learning on network security.

show abstract

“…Overfittingis a term used when the network model functions extremely good with the training data, but could not work well with the test data. In the overfitted network validation error goes up while the training error comes down [21].…”

Section: Introductionmentioning

confidence: 99%

Computer Science & Information Technology (CS & IT)

2021

View full text Add to dashboard Cite

In this work, deep CNN based model have been suggested for face recognition. CNN is employed to extract unique facial features and softmax classifier is applied to classify facial images in a fully connected layer of CNN. The experiments conducted in Extended YALE B and FERET databases for smaller batch sizes and low value of learning rate, showed that the proposed model has improved the face recognition accuracy. Accuracy rates of up to 96.2% is achieved using the proposed model in Extended Yale B database. To improve the accuracy rate further, preprocessing techniques like SQI, HE, LTISN, GIC and DoG are applied to the CNN model. After the application of preprocessing techniques, the improved accuracy of 99.8% is achieved with deep CNN model for the YALE B Extended Database. In FERET Database with frontal face, before the application of preprocessing techniques, CNN model yields the maximum accuracy of 71.4%. After applying the above-mentioned preprocessing techniques, the accuracy is improved to 76.3%

show abstract

A Comparison of Regularization Techniques in Deep Neural Networks

Cited by 92 publications

References 42 publications

Smart Grid Big Data Analytics: Survey of Technologies, Techniques, and Applications

Smart Grid Big Data Analytics: Survey of Technologies, Techniques, and Applications

A Spatiotemporal-Oriented Deep Ensemble Learning Model to Defend Link Flooding Attacks in IoT Network

Computer Science & Information Technology (CS & IT)

Contact Info

Product

Resources

About