arXiv:2009.13500
A priori estimates for classification problems using neural networks
원문 초록
We consider binary and multi-class classification problems using hypothesis classes of neural networks. For a given hypothesis class, we use Rademacher complexity estimates and direct approximation theorems to obtain a priori error estimates for regularized loss functionals.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
GeoVision Labeler: Zero-Shot Geospatial Classification with Vision and Language Models
Improving Generalizability of Kolmogorov-Arnold Networks via Error-Correcting Output Codes
Detecting immune cells with label-free two-photon autofluorescence and deep learning
Leveraging Cascaded Binary Classification and Multimodal Fusion for Dementia Detection through Spontaneous Speech
Self-Classification Enhancement and Correction for Weakly Supervised Object Detection
Multi-output Classification Framework and Frequency Layer Normalization for Compound Fault Diagnosis in Motor
토론
이 논문과 연결된 포럼 글이 아직 없습니다.