Deep Learning From a Control Vantage Point: Feedforward, Residual, Transformers, Large Language Models, And Selective State-Space Models
- 1 October 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Control Systems
- Vol. 46 (5) , 40-60
Abstract
No abstract availableFunding Information
- European Union (PID2024-156578NB-I00)
- U.S. National Science Foundation (2502536)
This publication has 67 references indexed in Scilit:
- Measure-to-Measure Interpolation Using TransformersFoundations of Computational Mathematics, 2026
- Fitting an immersed submanifold to data via Sussmann’s orbit theoremMathematics of Control, Signals, and Systems, 2025
- Deep limits of residual neural networksResearch in the Mathematical Sciences, 2022
- Control on the Manifolds of Mappings with a View to the Deep LearningJournal of Dynamical and Control Systems, 2021
- A Proposal on Machine Learning via Dynamical SystemsCommunications in Mathematics and Statistics, 2017
- Runge-Kutta methods in optimal control and the transformed adjoint systemNumerische Mathematik, 2000
- Robust Nonlinear Control Design1996
- Approximation by superpositions of a sigmoidal functionMathematics of Control, Signals, and Systems, 1989
- Learning Process in an Asymmetric Threshold Network1986
- A logical calculus of the ideas immanent in nervous activityBulletin of Mathematical Biology, 1943