Enhanced Neural Architecture Search Using Super Learner and Ensemble Approaches

Lankford, Seamus; Grimes, Diarmuid

doi:10.1145/3456126.3456133

Cited by 3 publications

(1 citation statement)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Akan tetapi, terdapat algoritme stacking yang lebih mutakhir daripada Stacked Generalization, yaitu Super Learner yang mengombinasikan pembelajar dasar dengan dibobotkan secara optimal terhadap fungsi kerugian (loss function) atau fungsi obyektif tertentu. Dalam beberapa penelitian pada domain lain, telah ditunjukkan bahwa Super Learner menghasilkan prediksi dengan keakuratan yang lebih baik daripada model Stacked Generalization [8][9]. Oleh sebab itu, penelitian ini membangun model prediksi dropout menggunakan algoritme Super Learner yang terdiri atas pembelajar dasar berupa LogReg, KNN, SVM, NB, RF, dan Extreme Gradient Boosting (XGBoost).…”

Section: Pendahuluanunclassified

Implementasi Prediksi Siswa Dropout pada MOOC Menggunakan Metode Stacking Super Learner dalam Lingkungan Komputasi Berkinerja Tinggi

Rahmi,

Djunaidy,

Akbar

2024

JTITS

View full text Add to dashboard Cite

Permasalahan utama di berbagai platform MOOC (massive open online course), yaitu tingginya tingkat dropout yang bahkan dapat mencapai 91%-93%. Hal ini tentu berdampak terhadap profitabilitas bisnis MOOC. Oleh sebab itu, diperlukan model prediksi siswa dropout pada MOOC untuk memungkinkan adanya intervensi pencegahan dropout. Namun, besarnya ukuran data siswa MOOC membuat proses pemodelan tersebut memerlukan komputasi yang tinggi. Dengan melihat permasalahan tersebut, maka penelitian ini membangun model prediksi menggunakan metode stacking yang mutakhir, yakni Super Learner, dan dikomputasikan secara paralel menggunakan GPU atau CPU dalam lingkungan komputasi berkinerja tinggi. Pembelajar dasar yang menyusun model Super Learner meliputi Logistic Regression, KNN, SVM, Naïve Bayes, Random Forest, dan XGBoost, sedangkan metalearner yang dieksperimenkan adalah NNloglik (non-negative binomial likelihood maximization) dan AUC-maxim (AUC maximization). Hasil eksperimen menunjukkan bahwa Super Learner dengan meta-learner AUC-maxim maupun NNloglik berhasil mengungguli kinerja model pembelajar dasar dan model yang menggunakan metode stacking lainnya, yaitu Stacked Generalization. Kedua model tersebut mencapai skor F1 secara berurutan sebesar 0,90139 dan 0,90126. Di samping itu, ditemukan bahwa paralelisasi GPU pada percobaan ini menghasilkan speedup komputasi hingga 2,4-23,3 kali lebih unggul daripada paralelisasi pada CPU.

show abstract

Section: Pendahuluanunclassified

Implementasi Prediksi Siswa Dropout pada MOOC Menggunakan Metode Stacking Super Learner dalam Lingkungan Komputasi Berkinerja Tinggi

Rahmi,

Djunaidy,

Akbar

2024

JTITS

View full text Add to dashboard Cite

show abstract

High performance machine learning approach for reference evapotranspiration estimation

Aly,

Darwish,

Aly

2023

Stoch Environ Res Risk Assess

View full text Add to dashboard Cite

Accurate reference evapotranspiration (ET0) estimation has an effective role in reducing water losses and raising the efficiency of irrigation water management. The complicated nature of the evapotranspiration process is illustrated in the amount of meteorological variables required to estimate ET0. Incomplete meteorological data is the most significant challenge that confronts ET0 estimation. For this reason, different machine learning techniques have been employed to predict ET0, but the complicated structures and architectures of many of them make ET0 estimation very difficult. For these challenges, ensemble learning techniques are frequently employed for estimating ET0, particularly when there is a shortage of meteorological data. This paper introduces a powerful super learner ensemble technique for ET0 estimation, where four machine learning models: Extra Tree Regressor, Support Vector Regressor, K-Nearest Neighbor and AdaBoost Regression represent the base learners and their outcomes used as training data for the meta learner. Overcoming the overfitting problem that affects most other ensemble methods is a significant advantage of this cross-validation theory-based approach. Super learner performances were compared with the base learners for their forecasting capabilities through different statistical standards, where the results revealed that the super learner has better accuracy than the base learners, where different combinations of variables have been used whereas Coefficient of Determination (R2) ranged from 0.9279 to 0.9994 and Mean Squared Error (MSE) ranged from 0.0026 to 0.3289 mm/day but for the base learners R2 ranged from 0.5592 to 0.9977, and MSE ranged from 0.0896 to 2.0118 mm/day therefore, super learner is highly recommended for ET0 prediction with limited meteorological data.

show abstract

Measuring the efficiency of banks using high-performance ensemble technique

Thabet,

Darwish,

Ali

2024

Neural Comput & Applic

View full text Add to dashboard Cite

The importance of technology and managerial risk management in banks has increased due to the financial crisis. Banks are the most affected since there are so many of them with poor financial standing. Due to this problem, an unstable and inefficient financial system causes economic stagnation in both the banking sector and overall economy. Data envelopment analysis (DEA) has been used to examine decision-making units (DMUs) performance to enhance efficiency. Currently, with the rapid growth of big data, adding more DMUs will likely require a large amount of memory and CPU time on the computer system, which will be the biggest challenge. As a result, machine learning (ML) approaches have been used to analyze financial institution performance, but many of them have variances in predictions or model stability, making measuring bank efficiency extremely difficult. For this, ensemble learning is commonly used to evaluate the performance of financial institutions in this context. This paper presents a robust super learner ensemble technique for assessing bank efficiency, with four machine learning models serving as base learners. These models are the support vector machine (SVM), K-nearest neighbors (KNN), random forest (RF), and AdaBoost classifier (ADA) which represent the base learners and their results utilized to train the meta-learner. The super learner (SL) approach is an extension of the stacking technique, which generates an ensemble based on cross-validation. One important benefit of this cross-validation theory-based technique is that it can overcome the overfitting issue that plagues most other ensemble approaches. When SL and base learners were compared for their forecasting abilities using different statistical standards, the results showed that the SL is superior to the base learners, where different variable combinations were used. The SL had accuracy (ACC) of 0.8636–0.9545 and F1-score (F1) of 0.9143–0.9714, while the basic learners had ACC of 0.5909–0.8182 and F1 of 0.6897–0.9143. So, SL is highly recommended for improving the accuracy of financial data forecasts, even with limited financial data.

show abstract

Enhanced Neural Architecture Search Using Super Learner and Ensemble Approaches

Cited by 3 publications

References 9 publications

Implementasi Prediksi Siswa Dropout pada MOOC Menggunakan Metode Stacking Super Learner dalam Lingkungan Komputasi Berkinerja Tinggi

Implementasi Prediksi Siswa Dropout pada MOOC Menggunakan Metode Stacking Super Learner dalam Lingkungan Komputasi Berkinerja Tinggi

High performance machine learning approach for reference evapotranspiration estimation

Measuring the efficiency of banks using high-performance ensemble technique

Contact Info

Product

Resources

About