Connectionists: CFP: Special Issue on STREAM LEARNING - IEEE Transactions on Neural Networks and Learning Systems

[Carlos]

CALL FOR PAPERS

IEEE Transactions on Neural Networks and Learning Systems

Special Issue on STREAM LEARNING

Deadline: 15 December 2021

Introduction

In recent years, machine learning from streaming data (called Stream
Learning) has enjoyed tremendous growth and exhibited a wealth of
development at both the conceptual and application levels. Stream
Learning is highly visible in both the machine learning and data science
fields and become a new hot direction in recent years. Research
developments in Stream Learning include learning under concept drift
detection (whether a drift occurs), understanding (where, when, and how
a drift occurs), and adaptation (to actively or passively update
models). Recently we have seen several new successful developments in
Stream Learning such as massive stream learning algorithms; incremental
and online learning for streaming data; and streaming data-based
decision-making methods. These developments have demonstrated how Stream
Learning technologies can contribute to the implementation of machine
learning capability in dynamic systems. We have also witnessed
compelling evidence of successful investigations on the use of Stream
Learning to support business real-time prediction and decision making.

In light of these observations, it is instructive, vital, and timely to
offer a unified view of the current trends and form a broad forum for
the fundamental and applied research as well as the practical
development of Stream Learning for improving machine learning, data
science and practical decision support systems of business. This special
issue aims at reporting the progress in fundamental principles;
practical methodologies; efficient implementations; and applications of
Stream Learning methods and related applications. The special issue also
welcomes contributions in relation to data streams, incremental learning
and reinforcement learning in data streaming situations.

Scope of the Special Issue

We invite submissions on all topics of Stream Learning, including but
not limited to:

• Data stream prediction

• Concept drift detection, understanding and adaptation

• Recurrent concepts

• Experimental setup and Evaluation methods for stream learning

• Reinforcement learning on streaming data

• Streaming data-based real-time decision making

• Ensemble methods for stream learning

• Auto machine learning for stream algorithms

• Neural networks for big data streams

• Transfer learning for streaming data

• Real-world applications of stream learning

• Active learning for streaming data

• Online learning for streaming data

• Imbalance learning for streaming data

• Lifelong learning for streaming data

• Incremental learning for streaming data

• Continuous learning for streaming data

• Clustering for streaming data

• Audio/speech/music streams processing

• Stream learning benchmark datasets

• Multi-drift and multi-stream learning

• Stream processing platforms


Timeline

• Submission deadline: Dec 15, 2021

• Notification of first review: Feb 1, 2022

• Submission of revised manuscript: May 1, 2022

• Notification of final decision: July 1, 2022

Guest Editors

• Jie Lu (University of Technology Sydney, Australia)

• Joao Gama (University of Porto, Portugal)

• Xin Yao (Southern University of Science and Technology, China)

• Leandro Minku (University of Birmingham, UK)

Submission Instructions

- Read the Information for Authors at http://cis.ieee.org/tnnls

- Submit your manuscript at the TNNLS webpage
(http://mc.manuscriptcentral.com/tnnls) and follow the submission
procedure. Please, clearly indicate on the first page of the manuscript
and in the cover letter that the manuscript is submitted to this special
issue. Early submissions are welcome.


Carlos Ferreira


ISEP | Instituto Superior de Engenharia do Porto
Rua Dr. António Bernardino de Almeida, 431
4249-015 Porto - PORTUGAL
tel. +351 228 340 500 | fax +351 228 321 159
mail at isep.ipp.pt | www.isep.ipp.pt