Depth Selection for Deep ReLU Nets in Feature Extraction and Generalization

• Published in: IEEE transactions on pattern analysis and machine intelligence Vol. 44; no. 4; pp. 1853 - 1868
• Main Authors: Han, Zhi, Yu, Siquan, Lin, Shao-Bo, Zhou, Ding-Xuan
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.04.2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Artificial neural networks; Cognitive tasks; Data mining; Deep learning; Deep nets; Earthquake prediction; Feature extraction; feature extractions; generalization; Humans; learning theory; Machine Learning; Machine learning algorithms; Neural Networks, Computer; Optimization; Pattern recognition; Task analysis

Deep learning is recognized to be capable of discovering deep features for representation learning and pattern recognition without requiring elegant feature engineering techniques by taking advantages of human ingenuity and prior knowledge. Thus it has triggered enormous research activities in machi...