English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Self-learning Machines based on Hamiltonian Echo Backpropagation

Lopez-Pastor, V., & Marquardt, F. (2021). Self-learning Machines based on Hamiltonian Echo Backpropagation. arXiv, 2103.04992.

Item is

Files

show Files
hide Files
:
arXiv.2103.04992.pdf (Any fulltext), 3MB
Name:
arXiv.2103.04992.pdf
Description:
-
Visibility:
Public
MIME-Type / Checksum:
application/pdf / [MD5]
Technical Metadata:
Copyright Date:
-
Copyright Info:
-
License:
-
:
21_Self-learning.png (Supplementary material), 52KB
Name:
21_Self-learning.png
Description:
-
Visibility:
Public
MIME-Type / Checksum:
image/png / [MD5]
Technical Metadata:
Copyright Date:
-
Copyright Info:
-
License:
-

Locators

show

Creators

show
hide
 Creators:
Lopez-Pastor, Victor1, Author
Marquardt, Florian1, Author              
Affiliations:
1Marquardt Division, Max Planck Institute for the Science of Light, Max Planck Society, ou_2421700              

Content

show
hide
Free keywords: -
 Abstract: A physical self-learning machine can be defined as a nonlinear dynamical system that can be trained on data (similar to artificial neural networks), but where the update of the internal degrees of freedom that serve as learnable parameters happens autonomously. In this way, neither external processing and feedback nor knowledge of (and control of) these internal degrees of freedom is required. We introduce a general scheme for self-learning in any time-reversible Hamiltonian system. We illustrate the training of such a self-learning machine numerically for the case of coupled nonlinear wave fields.

Details

show
hide
Language(s): eng - English
 Dates: 2021-03-082021-03-08
 Publication Status: Published online
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: arXiv: 2103.04992
 Degree: -

Event

show

Legal Case

show

Project information

show

Source 1

show
hide
Title: arXiv
Source Genre: Commentary
 Creator(s):
Affiliations:
Publ. Info: -
Pages: - Volume / Issue: - Sequence Number: 2103.04992 Start / End Page: - Identifier: -