SAFETYLIT WEEKLY UPDATE

We compile citations and summaries of about 400 new articles every week.
RSS Feed

HELP: Tutorials | FAQ
CONTACT US: Contact info

SafetyLit Journal Details

We are unable to provide photocopies of any the articles and reports abstracted in SafetyLit updates. Where possible, links have been provided to the publisher of the material and contact information for the corresponding author is listed. Please consider asking your library to subscribe to the journals from which these abstracts have been gathered.

To recommend a journal for this list please: Send SafetyLit an Email Message


Evolving systems (Berlin)

Abbreviation: Evol. Syst. (Berl.)

Published by: Holtzbrinck Springer-Nature

Publisher Location: Heidelberg, Germany

Journal Website:
https://link.springer.com/journal/12530/volumes-and-issues


Range of citations in the SafetyLit database: 2017; 8(2) -- 2024; ePub(ePub)

Publication Date Range: 2010 --

Title began with volume (issue): 1(1)

Number of articles from this journal included in the SafetyLit database: 5
(Download all articles from this journal in CSV format.)

pISSN = 1868-6478 | eISSN = 1868-6486
LCCN = 2018207387 | OCLC = 649520232


Find a library that holds this journal: http://worldcat.org/issn/18686478

Journal Language(s): English


Aims and Scope (from publisher): Evolving Systems covers surveys, methodological, and application-oriented papers in the area of dynamically evolving systems addressing continual (life-long) learning, open-set classification, self-learning and self-developing, self-evolving models and systems. Evolving systems are inspired by the idea of system model evolution in a dynamically changing and evolving environment. In contrast to the standard approach in machine learning, mathematical modelling, and related disciplines where the model structure is assumed and fixed a priori and the problem is primarily focused on parametric optimisation, evolving systems allow the learning representations and the model structure or architecture to gradually change/evolve. The aim of such continuous or life-long learning and domain adaptation is self-organisation. It can adapt to new data patterns, is more suitable for streaming data, transfer learning and can recognise and learn from unknown and unpredictable data patterns. Such properties are critically important for autonomous, robotic systems that continue learning and adapting after being designed (at run time).
Evolving Systems solicits publications that address the problems of all aspects of system modelling, clustering, classification, prediction, anomaly detection and control in non-stationary, unpredictable environments and describe new methods and approaches for their design.