Role of Locality and Weight Sharing in Image-Based Tasks: A Sample Complexity Separation between CNNs, LCNs, and FCNs

arXiv:2403.15707v1 Announce Type: new
Abstract: Vision tasks are characterized by the properties of locality and translation invariance. The superior performance of convolutional neural networks (CNNs) on these tasks is widely attributed to the inductive bias of locality and weight sharing baked into their architecture. Existing attempts to quantify the statistical benefits of these biases in CNNs over locally connected convolutional neural networks (LCNs) and fully connected neural networks (FCNs) fall into one of the following categories: either they disregard the …

abstract arxiv bias cnns complexity convolutional neural networks cs.ai cs.lg image inductive networks neural networks performance role sample stat.ml tasks translation type vision