Towards an optimal set of initial weights for a Deep Neural Network architecture

Saadi, Abdelhalim A.; Belhadef, Hacene

doi:10.14311/nnw.2019.29.025

Cited by 5 publications

(3 citation statements)

References 12 publications

(16 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This refers to a reasonable ANN model with the condition that the training error should be small, and the difference between the training error and the predicted error should be also small. Otherwise, it is an overfitting or underfitting ANN model (Briscoe and Feldman, 2011;Chang et al, 2012;Xiao et al, 2013;Lee et al, 2016;Belkin et al, 2019;Mehta et al, 2019;Saadi and Belhadef, 2019;Doroudi, 2020). Therefore, to verify the rationality of the both BPNN models of this study, we analyzed the training errors in the training process and predicted errors in the predicted process.…”

Section: Resultsmentioning

confidence: 95%

The Possibility of Real-Time and Long-Term Prediction for Geomagnetic Storms Using Neural Network

Lin

2022

Preprint

View full text Add to dashboard Cite

Two backpropagation neural network (BPNN) models were constructed to predict two historic geomagnetic storms that occurred in September 1999 and October 2003. The Disturbance storm time (Dst) indices from January 1, 1999, to December 31, 2014 (Coordinated Universal Time, UTC), were used as the training and test datasets for cross-validation in order to verify and validate the reliability and robustness of the two BPNN models, and yielded reasonable, predicted results. A large correlation coefficient (R) and low root mean square error (RMSE) were obtained, verifying the reliability of the two BPNN models. The predicted Dst indices can be provided for giving inputs in advance (i.e., any future time). Therefore, this analyzed method can serve as an excellent real-time prediction (RTP). To test the ability and possibility of the long-term prediction (LTP) obtained using the two BPNN models, the Dst indices were examined, which corresponded to two significant historic large geomagnetic storms that occurred in August 1972 and March 1989. For the both BPNN models, after evaluating their learning procedure, the time-dependence of LTP, the dependence of the predicted errors on the time period length of training datasets, and the variance by learning process, we found that they were stable models for the RTP and LTP.

show abstract

Section: Resultsmentioning

confidence: 95%

The Possibility of Real-Time and Long-Term Prediction for Geomagnetic Storms Using Neural Network

Lin

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…An IT project extension forecast is a tabular binary classification problem, with positive samples representing the completed projects and negative samples the uncompleted projects. We used a two-stage approach based on data analysis and the concept of the center of gravity [39]. e neural network was trained on a set of unbalanced data of the centers of mass from an a priori knowledge base (the first stage involved finding local minima close to the global minimum, and successful training was indicated when the local minima were relative to the global minimum).…”

Section: Experiments Setupmentioning

confidence: 99%

Meta-IP: An Imbalanced Processing Model Based on Meta-Learning for IT Project Extension Forecasts

Zhang

Han

et al. 2022

Mathematical Problems in Engineering

View full text Add to dashboard Cite

With increasing developments in information technology, IT projects have received widespread attention. However, the success rate of large information technology projects is extremely low. Most current extension forecast models are designed based on a balanced number of samples and require a large amount of training data to achieve an acceptable prediction result. Constructing an effective extension forecast model with a small number of actual training samples and imbalanced data remains a challenge. This paper proposes a Meta-IP model based on transferable knowledge bases with few-shot learning and a model-agnostic meta-learning improvement algorithm to solve the problems of sample scarcity and data imbalance. The experimental results show that Meta-IP not only outperforms many current imbalance processing strategies but also resolves the problem of having too few samples. This provides a new direction for IT project extension forecasts.

show abstract

“…There are several architectures that can be implemented when it comes to deep learning (Saadi & Belhadef, 2019;Mansuri & Patel, 2021). Each of these architectures has its uses and compatibilities with certain applications.…”

Section: Introductionmentioning

confidence: 99%

Deep learning for detecting distresses in buildings and pavements: a critical gap analysis

Elghaish

Matarneh

Talebi

et al. 2021

View full text Add to dashboard Cite

Purpose The massive number of pavements and buildings coupled with the limited inspection resources, both monetary and human, to detect distresses and recommend maintenance actions lead to rapid deterioration, decreased service life, lower level of service and increased community disruption. Therefore, this paper aims at providing a state-of-the-art review of the literature with respect to deep learning techniques for detecting distress in both pavements and buildings; research advancements per asset/structure type; and future recommendations in deep learning applications for distress detection. Design/methodology/approach A critical analysis was conducted on 181 papers of deep learning-based cracks detection. A structured analysis was adopted so that major articles were analyzed according to their focus of study, used methods, findings and limitations. Findings The utilization of deep learning to detect pavement cracks is advanced compared to assess and evaluate the structural health of buildings. There is a need for studies that compare different convolutional neural network models to foster the development of an integrated solution that considers the data collection method. Further research is required to examine the setup, implementation and running costs, frequency of capturing data and deep learning tool. In conclusion, the future of applying deep learning algorithms in lieu of manual inspection for detecting distresses has shown promising results. Practical implications The availability of previous research and the required improvements in the proposed computational tools and models (e.g. artificial intelligence, deep learning, etc.) are triggering researchers and practitioners to enhance the distresses’ inspection process and make better use of their limited resources. Originality/value A critical and structured analysis of deep learning-based crack detection for pavement and buildings is conducted for the first time to enable novice researchers to highlight the knowledge gap in each article, as well as building a knowledge base from the findings of other research to support developing future workable solutions.

show abstract

Towards an optimal set of initial weights for a Deep Neural Network architecture

Cited by 5 publications

References 12 publications

The Possibility of Real-Time and Long-Term Prediction for Geomagnetic Storms Using Neural Network

The Possibility of Real-Time and Long-Term Prediction for Geomagnetic Storms Using Neural Network

Meta-IP: An Imbalanced Processing Model Based on Meta-Learning for IT Project Extension Forecasts

Deep learning for detecting distresses in buildings and pavements: a critical gap analysis

Contact Info

Product

Resources

About