Discrete Deep Feature Extraction: A Theory and New Architectures
원문 초록
First steps towards a mathematical theory of deep convolutional neural networks for feature extraction were made---for the continuous-time case---in Mallat, 2012, and Wiatowski and B\"olcskei, 2015. This paper considers the discrete case, introduces new convolutional neural network architectures, and proposes a mathematical framework for their analysis. Specifically, we establish deformation and translation sensitivity results of local and global nature, and we investigate how certain structural properties of the input signal are reflected in the corresponding feature vectors. Our theory applies to general filters and general Lipschitz-continuous non-linearities and pooling operators. Experiments on handwritten digit classification and facial landmark detection---including feature importance evaluation---complement the theoretical findings.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
CycleVAR: Repurposing Autoregressive Model for Unsupervised One-Step Image Translation
CycleDistill: Bootstrapping Machine Translation using LLMs with Cyclical Distillation
MOL: Joint Estimation of Micro-Expression, Optical Flow, and Landmark via Transformer-Graph-Style Convolution
Enhancing interpretability of rule-based classifiers through feature graphs
Gender Bias in English-to-Greek Machine Translation
Mutual-Supervised Learning for Sequential-to-Parallel Code Translation
토론
이 논문과 연결된 포럼 글이 아직 없습니다.