A Survey on Ensemble Learning under the Era of Deep Learning

By Y. Yang et al

Read the original document by opening this link in a new tab.

Table of Contents

1 Introduction
2 Data Analysis of Published Works
2.1 Prosperity of EL
2.2 Gap between EDL and TEL
3 Traditional Ensemble Learning
3.1 Preliminary
3.2 Methodology of TEL
3.3 Well-known implementations for methodology of TEL

Summary

This document presents a survey on ensemble learning under the era of deep learning. It discusses the significant advantages of ensemble learning based on deep neural networks, highlighting the challenges and advancements in this field. The authors analyze the prosperity of ensemble learning and the gap between ensemble deep learning (EDL) and traditional ensemble learning (TEL). Traditional ensemble learning involves generating base learners and forming an ensemble learner for better generalization. Various well-known implementations for methodology of TEL are discussed, including different learning strategies and ensembling criteria. The document provides insights into the development and challenges of ensemble learning in the context of deep learning.