Recurrent neural network ODE output for classification problems follows the replicator dynamics
J Barreiro-Gomez, JI Poveda - IEEE Control Systems Letters, 2023 - ieeexplore.ieee.org
This letter establishes a novel relationship between a class of recurrent neural networks and
certain evolutionary dynamics that emerge in the context of population games. Specifically, it …
certain evolutionary dynamics that emerge in the context of population games. Specifically, it …
An analysis of the impact of subsampling on the neural network error surface
C Dennis, A Engelbrecht, BM Ombuki-Berman - Neurocomputing, 2021 - Elsevier
This paper empirically analyses the impact of changes to the set of training examples on the
neural network error surface. Specific quantitative characteristics of the error surface related …
neural network error surface. Specific quantitative characteristics of the error surface related …
A game-theoretic perspective of deep neural networks
C Ren, Z Wu, D Xu, W Xu - Theoretical Computer Science, 2023 - Elsevier
We devote this paper to a theoretic analysis of deep neural networks from a game-
theoretical perspective. We consider a general deep neural network D with linear activation …
theoretical perspective. We consider a general deep neural network D with linear activation …
A game-theoretic analysis of deep neural networks
C Ren, Z Wu, D Xu, W Xu - … Aspects in Information and Management: 15th …, 2021 - Springer
As an important part of machine learning, deep learning has been intensively used in
various fields relevant to data science. Despite of its popularity in practice, it is still of …
various fields relevant to data science. Despite of its popularity in practice, it is still of …