Different scaling of linear models and deep learning in UKBiobank brain images versus machine-learning datasets

Abstract

Recently, deep learning has unlocked unprecedented success in various domains, especially using images, text, and speech. However, deep learning is only beneficial if the data have nonlinear relationships and if they are exploitable at available sample sizes. We systematically profiled the performance of deep, kernel, and linear models as a function of sample size on UKBiobank brain images against established machine learning references. On MNIST and Zalando Fashion, prediction accuracy consistently improves when escalating from linear models to shallow-nonlinear models, and further improves w

Abstract by Marc-André Schulz; B.T. Thomas Yeo; Joshua T Vogelstein; Janaina Mourao-Miranada; Jakob Nikolas Kather; Konrad P. Körding; Blake A. Richards; Danilo Bzdok, Nature Communications (2020) — licensed CC BY 4.0.

Related failures