Data Selection for Neural Networks

Kordos, Mirosław

doi:10.4467/20838476si.16.012.6193

Cited by 6 publications

(5 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our results indicate that the use of the ENN algorithm in our framework significantly improves training time, a finding consistent with previous studies [27][28][29]. However, reducing the size of the training dataset does slightly impact the accuracy of our deep learning models.…”

Section: Resultssupporting

confidence: 90%

“…Instance Reduction Techniques (IR), sometimes referred to as Instance Selection Algorithms (IS), reduce the size of the training dataset by selecting which instances to keep for use in the generalization process [14]. Instance Reduction Techniques are most commonly utilized in the context of Instance-Based Learning (IBL) [26], although they are used to improve classification accuracy by removing noisy instances, speed up neural networks [27,28], and reduce excessive memory storage [29].…”

Section: Instance Reduction Techniques (Ir)mentioning

confidence: 99%

See 1 more Smart Citation

Privacy-Preserving Deep Learning Framework Based on Restricted Boltzmann Machines and Instance Reduction Algorithms

Alshammari,

El Hindi

2024

Applied Sciences

View full text Add to dashboard Cite

The combination of collaborative deep learning and Cyber-Physical Systems (CPSs) has the potential to improve decision-making, adaptability, and efficiency in dynamic and distributed environments. However, it brings privacy, communication, and resource restrictions concerns that must be properly addressed for successful implementation in real-world CPS systems. Various privacy-preserving techniques have been proposed, but they often add complexity and decrease accuracy and utility. In this paper, we propose a privacy-preserving deep learning framework that combines Instance Reduction Techniques (IR) and the Restricted Boltzmann Machine (RBM) to preserve privacy while overcoming the limitations of other frameworks. The RBM encodes training data to retain relevant features, and IR selects the relevant encoded instances to send to the server for training. Privacy is preserved because only a small subset of the training data is sent to the server. Moreover, it is sent after encoding it using RBM. Experiments show that our framework preserves privacy with little loss of accuracy and a substantial reduction in training time. For example, using our framework, a CNN model for the MNIST dataset achieves 96% accuracy compared to 99% in a standard collaborative framework (with no privacy measures taken), with training time reduced from 133.259 s to 99.391 s. Our MLP model for MNIST achieves 97% accuracy compared to 98% in the standard collaborative framework, with training time reduced from 118.146 s to 87.873 s. Compared to other studies, our method is a simple approach that protects privacy, maintains the utility of deep learning models, and reduces training time and communication costs.

show abstract

Section: Resultssupporting

confidence: 90%

Section: Instance Reduction Techniques (Ir)mentioning

confidence: 99%

Privacy-Preserving Deep Learning Framework Based on Restricted Boltzmann Machines and Instance Reduction Algorithms

Alshammari,

El Hindi

2024

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…Based on Demuth et al ( 2014 ) and Kordos ( 2016 ), the choice of data set size is closely related to the choice of the number of neurons in the neural network (explained in the network architecture, section Research Methodology and Experimental Design). In our case, given that the entire neural network training process is iterative, it is the network performance that indicates that we have enough data.…”

Section: Methodological Approachmentioning

confidence: 99%

Predicting Big Data Adoption in Companies With an Explanatory and Predictive Model

et al. 2021

View full text Add to dashboard Cite

The purpose of this paper is to identify the factors that affect the intention to use Big Data Applications in companies. Research into Big Data usage intention and adoption is scarce and much less from the perspective of the use of these techniques in companies. That is why this research focuses on analyzing the adoption of Big Data Applications by companies. Further to a review of the literature, it is proposed to use a UTAUT model as a starting model with the update and incorporation of other variables such as resistance to use and perceived risk, and then to perform a neural network to predict this adoption. With respect to this non-parametric technique, we found that the multilayer perceptron model (MLP) for the use of Big Data Applications in companies obtains higher AUC values, and a better confusion matrix. This paper is a pioneering study using this hybrid methodology on the intention to use Big Data Applications. The result of this research has important implications for the theory and practice of adopting Big Data Applications.

show abstract

“…Several studies have demonstrated the potential of feature selection methods to improve predictors in recent years ( [5], [9], [41], [47]). Since feature selection aims to reduce the dimension of a dataset by selecting variables that are relevant to the predicting attribute(s), recursive feature elimination (RFE) has been performed to eliminate some of the original input features and retain the minimum subset of features that yield the best classification performance.…”

Section: Reviewsmentioning

confidence: 99%

A Real Estate Valuation Model Using Boosted Feature Selection

et al. 2021

View full text Add to dashboard Cite

To estimate real estate values, a complex valuation model based on artificial neural network (ANN) has been established as a successful means in modern machine learning research, specifically when high-dimensional data are available. Unfortunately, the real estate data in many locations, such as Thailand, are quite limited in terms of features. Hence, it becomes mandatory to reduce the complexity using feature selection techniques. These techniques aim to improve performance by identifying significant factors and help decrease the computational overload and model construction. However, due to the lack of explicability and interpretability in ANNs, the analysis of input factors cannot be explained directly by model composition. In this research, we apply a combination of a boosting strategy and input sensitivity analysis in an improved Garson's algorithm to perform feature selection that can adjust its selection criteria through each iteration on an ANN model. This proposed technique is then compared with other traditional feature selection techniques using synthetic data and real-world house valuation data. The results show that our model can maintain the sensitivity coefficient for every informative feature. The technique of this study provides a set of features that influences the house price and implies the character of each specific area. It also contributes to statistical improvement in most valuation cases, with a lower error than that obtained without a selected feature dataset, and it placed in the top 24% of the public leaderboard in the Zillow Prize competition.

show abstract

Data Selection for Neural Networks

Cited by 6 publications

References 20 publications

Privacy-Preserving Deep Learning Framework Based on Restricted Boltzmann Machines and Instance Reduction Algorithms

Privacy-Preserving Deep Learning Framework Based on Restricted Boltzmann Machines and Instance Reduction Algorithms

Predicting Big Data Adoption in Companies With an Explanatory and Predictive Model

A Real Estate Valuation Model Using Boosted Feature Selection

Contact Info

Product

Resources

About