A Statistical-Modelling Approach to Feedforward Neural Network Model Selection

arXiv:2207.04248v5 Announce Type: replace-cross
Abstract: Feedforward neural networks (FNNs) can be viewed as non-linear regression models, where covariates enter the model through a combination of weighted summations and non-linear functions. Although these models have some similarities to the approaches used within statistical modelling, the majority of neural network research has been conducted outside of the field of statistics. This has resulted in a lack of statistically-based methodology, and, in particular, there has been little emphasis on model parsimony. Determining the …

abstract arxiv combination cs.lg functions linear linear regression modelling model selection network networks neural network neural networks non-linear regression research statistical stat.me through type