Wide and deep neural networks achieve consistency for classification.

ABSTRACT: While neural networks are used for classification tasks across domains, a long-standing open problem in machine learning is determining whether neural networks trained using standard procedures are consistent for classification, i.e., whether such models minimize the probability of misclassification for arbitrary data distributions. In this work, we identify and construct an explicit set of neural network classifiers that are consistent. Since effective neural networks in practice are typically both wide and deep, we analyze infinitely wide networks that are also infinitely deep. In particular, using the recent connection between infinitely wide neural networks and neural tangent kernels, we provide explicit activation functions that can be used to construct networks that achieve consisten

SUBMITTER: Radhakrishnan A 

PROVIDER: S-EPMC10083596 | biostudies-literature | 2023 Apr

REPOSITORIES: biostudies-literature