Jose Israel Rodriguez, Activation Degree Thresholds / Expressiveness of Polynomial NNs, 2025.10.07
Автор: CodEx Seminar
Загружено: 2026-01-24
Просмотров: 48
Описание:
Speaker: Jose Israel Rodriguez (University of Wisconsin)
Title: Activation Degree Thresholds and Expressiveness of Polynomial Neural Networks
Date: 2025.10.07
Abstract:
Polynomial neural networks are implemented in a range of applications and present an advantageous framework for theoretical machine learning. In this talk, we introduce the notion of the activation degree threshold of a network architecture. This expresses when the dimension of a neurovariety achieves its theoretical maximum. We show that activation degree thresholds of polynomial neural networks exist and provide an upper bound, resolving a conjecture on the dimension of neurovarieties associated to networks with high activation degree. Along the way, we will see several illustrative examples.
Повторяем попытку...
Доступные форматы для скачивания:
Скачать видео
-
Информация по загрузке:
