Infinite-dimensional reservoir computing
Reservoir computing approximation and generalization bounds are proved for a new concept class of input/output systems that extends the so-called generalized Barron functionals to a dynamic context. This new class is characterized by the readouts with a certain integral representation built on infin...
Saved in:
Main Authors: | Gonon, Lukas, Grigoryeva, Lyudmila, Ortega, Juan-Pablo |
---|---|
Other Authors: | School of Physical and Mathematical Sciences |
Format: | Article |
Language: | English |
Published: |
2024
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/180739 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
Similar Items
-
Dimension reduction in recurrent networks by canonicalization
by: Grigoryeva, Lyudmila, et al.
Published: (2022) -
Learning strange attractors with reservoir systems
by: Grigoryeva, Lyudmila, et al.
Published: (2023) -
Transport in reservoir computing
by: Manjunath, G., et al.
Published: (2023) -
Tracing curves in the plane: geometric-invariant learning from human demonstrations
by: Turlapati, Sri Harsha, et al.
Published: (2024) -
Dynamic Ferroelectric Transistor-based Reservoir Computing for Spatiotemporal Information Processing
by: Ngoc Thanh Duong, et al.
Published: (2023)